DEV Community

Cover image for Build your own custom AI CLI tools
Manuel Odendahl
Manuel Odendahl

Posted on

Build your own custom AI CLI tools

Originally posted on: scapegoat.dev

AI generated GO GO GHOST

I am notoriously distracted and both my long and short term memories are less reliable than a hobbyist's kubernetes cluster. After 20 years of python, I still can't remember what the arguments to split are.

Thankfully, these days are now over, as I can ask a just as clueless LLM to answer the myriad of questions I would otherwise have to google everyday (please don't use google, use kagi, you'll thank me later). Being part of a secret society of robo-scientists, I have been building some visionary software over the last couple of months, drawing inspiration from many sources, because writing software is about being in touch with the universe.

More prosaically, I have been writing some LLM-powered command line tools, as many people have before me and many people will after my bones are dust and my ideas forgotten. All the tools I present in this blog post have been written in a single day, because that's the world we now live in.

Some preliminary examples

Here is a little taste of the things that are possible with these tools.

All of these examples were built in a couple of hours altogether. By the end of the article, you will be able to build them too, with no code involved.

You might see a a mix of pinocchio commands and llmX commands. The llmX commands are just aliases to pinocchio prompts code X, the llmX-3.5 are aliases to use the gpt-3.5-turbo model (pinocchio prompts code X --openai-engine gpt-3.5-turbo).

Reversing a string in go

Let's start with a simple interview question: reverse a string in go.

the scapegoat dev

Getting some ffmpeg help

Too lazy for manpages? Extremely reliable LLM to the rescue!

the scapegoat dev

Getting some vim help

Some more reliable, trusted help.

the scapegoat dev

Creating a script to help us convert these goddamn videos

Recording these little screencast videos is tedious, let's get some help.

the scapegoat dev

Explaining a terraform file

What the heck did I do 2 months ago?

the scapegoat dev

Writing a bandcamp search client

Too lazy to read API docs? Just paste a curl request in there! Documentation is for chumps!

the scapegoat dev

Code review that genius code

I'm sure this won't miss a single thing. It sure is more annoying than my colleague Janine.

the scapegoat dev

Give the intern some advice

But don't be so blunt.

the scapegoat dev

Create some slides for the weekly review

Tufte said slides shouldn't have bullet points. We disagree.

the scapegoat dev

Installing pinocchio

In order for you, dear reader, to follow along on this adventure, you first need to install pinocchio. Nothing could be easier as we provide binaries for linux and mac (x86 and arm), as well as RPM and deb packages. All the GO GO GADGETS are also published on homebrew and as docker images, if that's your jam.

After configuring your OpenAI API key, you should be all set to go. For more precise instructions, check out the installation guide.

Geppetto - LLM framework

an AI generated robotic geppetto working on a robotic monkey

Over the last couple of months, like every other developer out there, I have been working on a LLM framework that will make it trivial to build AMAZING CRAZY STUFF.

The core architecture of this very advanced framework boils down to:

  • take input values
  • interpolate them into a big string using the go templating engine
  • sending the string over HTTP
  • print out the response

(This is why they call me senior engineer).

The framework's claim to fame, besides having a cool name (geppetto is a client for GPT and pinocchio, the puppet borne of geppetto's woodworking, is the CLI tool used to run applications built with the framework. Of course, LLMs being what they are, pinocchio often lies).

Declarative commands

Jokes aside, general consensus amongst the GO GO GOLEMS has it that geppetto and pinocchio are pretty cool. They are both based on the glazed framework, more precisely based on the Command abstraction.

This groundbreaking abstraction of a "general purpose command" consists of:

  • a set of input flags and parameters (which can be grouped into layers because having 800 flags tends to get overwhelming), each having a type, a default value and a description
  • a Run() function that executes the command
  • some kind of output (either structured tabular data, which is what glazed is built for, or just a sequence of bytes, in our case)

Most of the actual engineering in glazed focuses on:

  • making it easy to define flags declaratively (usually as YAML)
  • parsing flags at runtime (usually using the cobra framework)
  • running the actual Command by calling Run
  • processing the tabular output in a myriad of ways, none of which matter today

After handling \r\n and \n, converting between strings and integers is the second hardest engineering problem known to man. This is why this framework is senior principal staff engineer grade.

For example, the flags for the go command shown in the first video look like this:



flags:
  - name: additional_system
    type: string
    help: Additional system prompt
    default: ""
  - name: additional
    type: string
    help: Additional prompt
    default: ""
  - name: write_code
    type: bool
    help: Write code instead of answering questions
    default: false
  - name: context
    type: stringFromFiles
    help: Additional context from files
  - name: concise
    type: bool
    help: Give concise answers
    default: false
  - name: use_bullets
    type: bool
    help: Use bullet points in the answer
    default: false
  - name: use_keywords
    type: bool
    help: Use keywords in the answer
    default: false
arguments:
  - name: query
    type: stringList
    help: Question to answer
    required: true


Enter fullscreen mode Exit fullscreen mode

glazed provides a variety of standard types: strings, list of strings, objects, strings from files, booleans, integers, you name it.

These declarative flags as well as layers added by the application all get wired up as CLI flags. Because this is user-first development, the output is colored.

a screenshot of the pinocchio help

If we were to use something like parka, these flags would be exposed as REST APIs, HTML forms and file download URLs. For example, sqleton can be run as a webserver for easy querying of a database.



flags:
  - name: today
    type: bool
    help: Select only today's orders
    default: true
  - name: from
    type: date
    help: From date
  - name: to
    type: date
    help: To date
  - name: status
    type: stringList
    help: Batch status
  - name: limit
    help: Limit the number of results
    type: int
    default: 0
  - name: offset
    type: int
    help: Offset
    default: 0
  - name: order_by
    type: string
    default: id DESC
    help: Order by


Enter fullscreen mode Exit fullscreen mode

a screenshot of a pretty web form that corresponds to the flags above

But that is a story for another time.

GeppettoCommand - look ma, no code

Now that we know how to define a command's input parameters, let's get to what a geppetto command is actually made of.

A geppetto command:

  • uses its input parameters to interpolate a set of messages (system prompt, user messages, assistant messages)
  • fills out the parameters for a request to OpenAI's completion API
  • fires off a HTTP request
  • streams the output back to the standard output.

Geppetto supports specifying functions too, but I've never used them because I try to use boring technology, not the latest fancy shiny new thing.

None of this requires massive amounts of clever computation, which is why we can also fit all of this into the same YAML file. For example, the go command from before looks like this:



name: go
short: Answer questions about the go programming language
factories:
  openai:
    client:
      timeout: 120
    completion:
      engine: gpt-4
      temperature: 0.2
      max_response_tokens: 1024
      stream: true
flags:
# snip snip ...
system-prompt: |
  You are an expert golang programmer. You give concise answers for expert users.
  You give concise answers for expert users.
  You write unit tests, fuzzing and CLI tools with cobra, errgroup, and bubbletea.
  You pass context.Context around for cancellation.
  You use modern golang idioms.
prompt: |
  {{ if .write_code }}Write go code the following task.
  Output only the code, but write a lot of comments as part of the script.{{ else }}
  Answer the following question about go. Use code examples. Give a concise answer.
  {{ end }}
  {{ .query | join " " }}
  {{ .additional }}
  {{ if .context }}
    {{ .context }}
  {{ end }}
  {{ if .concise }}
    Give a concise answer, answer in a single sentence if possible, skip unnecessary explanations.
  {{ end }}
  {{ if .use_bullets }}
    Use bullet points in the answer.
  {{ end }}
  {{ if .use_keywords }}
      Use keywords in the answer.
  {{ end }}


Enter fullscreen mode Exit fullscreen mode

You can see here how we we first specify the OpenAI API parameters:

  • we are using the gpt-4 model per default (try using gpt-3.5-turbo for programming, I dare you)
  • with a reasonably low temperature.

Of course, all these settings can be overridden from the command line.

After the (omitted) flags definition from before, we get to the special sauce:

  • a system prompt template telling the LLM exactly who it is (or, giving it a special SYS token followed by some offputtingly prescriptive tokens with the hope that all this conjuring will cause future tokens to be tokens that are USEFUL TO ME)
  • a message prompt template that will be passed as a user message to the LLM, again with the hope that this little preamble will cause the model to generate something at least remotely useful. I think of it as having a fortune reader draw some language-shaped cards that tell me what code to write next

While what pinocchio does borders on magic (as all things having to do with LLMs), it is not too complicated to follow:

  • it interpolates the templates
  • it collects the system prompt and the prompt as messages
  • it sends off those messages to the openAI API
  • it outputs the streaming responses (if streaming is enabled) ### YAML is nice

The nice part (the really nice part) about being able to create "rich" command line applications using glazed and geppetto is that you can now experiment with prompt engineering by using command line flags instead of having to write custom test runners and data tables. This simple example-driven template is usually enough to reproduce most papers from 2021 and 2022, as shown by various datasets used in the Chain Of Thought paper.



name: example-driven
short: Show a chain of thought example
flags:
  - name: question
    type: string
    help: The question to ask
    required: true
  - name: problem
    type: string
    help: The problem to solve
    required: false
  - name: instructions
    type: string
    help: Additional instructions to follow
    required: false
  - name: examples
    type: objectListFromFile
    required: true
prompt: |
  {{ if .problem }}
  Problem: {{ .problem }}
  {{ end }}
  {{ range $i, $example := .examples }}
  Q: {{ $example.question }}
  A: {{ $example.answer }}
  {{ end }}
  {{ if .instructions }}
  Instructions: {{ .instructions }}
  {{ end }}
  Q: {{ .question }}
  A:


Enter fullscreen mode Exit fullscreen mode

And of course, it is entirely possible to generate GeppettoCommands using GeppettoCommands, as shown by this example which can be used to generate SqletonCommands (the same concept, but for SQL).

Using a GeppettoCommand that generates GeppettoCommands to generate itself risks immanentizing the eschaton and bringing singularity into being, so use these new-found powers with caution.



name: quine
short: Generate yourself!
flags:
  - name: example_goal
    short: Example goal
    type: string
    default:  Generate a program to generate itself.
  - name: instructions
    type: string
    help: Additional language specific instructions
    required: false
  - name: example
    type: stringFromFile
    help: Example program
    required: true
  - name: goal
    type: string
    help: The goal to be generated
    default: Generate a program to generate itself.
prompt: |
  Write a program by generating  a YAML describing a command line application with flags and a prompt template using
  go template expansion.
  The flags are used to interpolate the prompt template.

  Here is an example.

  --- GOAL: {{ .example_goal }}
  --- START PROGRAM
  {{ .example | indent 4 }}
  --- END 

  Generate a program to {{ .goal }}.

  {{ if .instructions }}{{ .instructions }}{{ end }}

  --- GOAL: {{ .goal }}
  --- START PROGRAM


Enter fullscreen mode Exit fullscreen mode

SQLETON excursion - generating SQL queries using generated SQL queries

an AI generated go go skull

Let's imagine that we want to generate SqletonCommands using the schema from a table in the database, but we are so lazy that we don't want to copy that schema. Wouldn't it be nice if we had a SqletonCommand to introspect a schema?



pinocchio examples code sqleton --topic "Create a command to output the schema of a table in mysql. It should take flags: tables, tables_like, columns, columns_like, type. Output the table name as column as well." 


Enter fullscreen mode Exit fullscreen mode

To which the LLM responds:

Here is an example of a command that outputs the schema of a table in MySQL using the provided YAML template:



name: schema
short: Output the schema of a table in MySQL.
flags:
  - name: tables
    type: stringList
    help: List of table names
  - name: tables_like
    type: stringList
    help: List of table name patterns to match
  - name: columns
    type: stringList
    help: List of column names
  - name: columns_like
    type: stringList
    help: List of column name patterns to match
  - name: type
    type: string
    help: Column data type
query: |
  SELECT
    TABLE_NAME AS table_name,
    COLUMN_NAME AS column_name,
    COLUMN_TYPE AS column_type,
    IS_NULLABLE AS is_nullable,
    COLUMN_KEY AS column_key,
    COLUMN_DEFAULT AS column_default,
    EXTRA AS extra
  FROM
    INFORMATION_SCHEMA.COLUMNS
  WHERE 1=1
  {{ if .tables }}
    AND TABLE_NAME IN ({{ .tables | sqlStringIn }})
  {{ end }}
  {{ if .tables_like }}
    AND (
      {{ range $index, $table := .tables_like }}
        TABLE_NAME LIKE '{{ $table }}'
        {{ if not (last $index .tables_like) }}
          OR
        {{ end }}
      {{ end }}
    )
  {{ end }}
  {{ if .columns }}
    AND COLUMN_NAME IN ({{ .columns | sqlStringIn }})
  {{ end }}
  {{ if .columns_like }}
    AND (
      {{ range $index, $column := .columns_like }}
        COLUMN_NAME LIKE '{{ $column }}'
        {{ if not (last $index .columns_like) }}
          OR
        {{ end }}
      {{ end }}
    )
  {{ end }}
  {{ if .type }}
    AND COLUMN_TYPE = '{{ .type }}'
  {{ end }}
  ORDER BY table_name


Enter fullscreen mode Exit fullscreen mode

In this example, the tables flag accepts a list of table names, the tables_like flag accepts a list of table name patterns to match using the LIKE operator, the columns flag accepts a list of column names, the columns_like flag accepts a list of column name patterns to match using the LIKE operator, and the type flag accepts a column data type.

The query uses the INFORMATION_SCHEMA.COLUMNS table to retrieve the schema information. The WHERE clause is dynamically generated based on the provided flags. The ORDER BY clause orders the results by the table name.

Note that the sqlStringIn function is used to generate the IN clause for string values, and the last function is used to determine if it is the last element in a list during iteration.

Storing that command as mysql schema, we can now easily introspect various tables, leveraging all the affordances provided by glazed.



❯ sqleton mysql schema --tables giftcards 
+------------+---------------+-----------------+-------------+------------+----------------+-------+
| table_name | column_name   | column_type     | is_nullable | column_key | column_default | extra |
+------------+---------------+-----------------+-------------+------------+----------------+-------+
| giftcards  | active        | tinyint         | NO          | MUL        | 0              |       |
| giftcards  | amount        | decimal(10,2)   | NO          |            | 0.00           |       |
| giftcards  | balance       | decimal(10,2)   | NO          |            | 0.00           |       |
| giftcards  | code          | varchar(200)    | NO          |            | <nil>          |       |
| giftcards  | created_at    | datetime        | YES         | MUL        | <nil>          |       |
| giftcards  | expired       | int             | YES         | MUL        | <nil>          |       |
| giftcards  | expires_at    | datetime        | YES         | MUL        | <nil>          |       |
| giftcards  | free_shipping | tinyint         | NO          | MUL        | 0              |       |
| giftcards  | id            | int unsigned    | NO          | PRI        | 0              |       |
| giftcards  | note          | mediumtext      | YES         |            | <nil>          |       |
| giftcards  | open_amount   | decimal(10,2)   | NO          |            | 0.00           |       |
| giftcards  | order_date    | date            | YES         | MUL        | <nil>          |       |
| giftcards  | order_id      | bigint unsigned | YES         | MUL        | 0              |       |
| giftcards  | order_number  | longtext        | YES         | MUL        | <nil>          |       |
| giftcards  | redeemed      | decimal(11,2)   | NO          |            | 0.00           |       |
| giftcards  | TYPE          | varchar(9)      | NO          | MUL        |                |       |
+------------+---------------+-----------------+-------------+------------+----------------+-------+


Enter fullscreen mode Exit fullscreen mode

Or slightly smaller:



❯ sqleton mysql schema --tables giftcards --columns-like '%order%' --output yaml --filter extra,column_default
- table_name: giftcards
  column_name: order_date
  column_type: date
  is_nullable: "YES"
  column_key: MUL
- table_name: giftcards
  column_name: order_id
  column_type: bigint unsigned
  is_nullable: "YES"
  column_key: MUL
- table_name: giftcards
  column_name: order_number
  column_type: longtext
  is_nullable: "YES"
  column_key: MUL


Enter fullscreen mode Exit fullscreen mode

We can easily use our new mysql schema command to create new SqletonCommands, say one to query our giftcards table.



❯ sqleton mysql schema \
       --tables giftcards \
       --fields column_name,column_type,is_nullable \
       --output yaml | 
  pinocchio examples code sqleton --ddl - \
     --topic "Giftcards from an ecommerce database, used as giftcards but also warranty and courtesy refunds." \ 
    --instructions "Don't create flags for individual amounts. Create a codes_like flag."


Enter fullscreen mode Exit fullscreen mode

To which the LLM responds:

Here is the updated YAML template for querying the giftcards table:



name: giftcards
short: Get giftcards from the database.
flags:
  - name: id
    type: intList
    help: List of giftcard ids
  - name: code
    type: stringList
    help: List of giftcard codes
  - name: active
    type: bool
    help: Giftcard active status
  - name: expired
    type: bool
    help: Giftcard expired status
  - name: expires_at
    type: date
    help: Giftcard expiration date
  - name: order_id
    type: int
    help: Order ID associated with the giftcard
  - name: order_number
    type: string
    help: Order number associated with the giftcard
  - name: redeemed
    type: float
    help: Giftcard redeemed amount
  - name: type
    type: string
    help: Giftcard type
  - name: codes_like
    type: stringList
    help: List of giftcard codes to filter by using LIKE queries
  - name: limit
    type: int
    help: Limit the number of results
    default: 0
  - name: offset
    type: int
    help: Offset 
    default: 0
  - name: order_by
    type: string
    default: created_at DESC
    help: Order by
query: |
  {{ if .explain }}
    EXPLAIN
  {{ end }}
  SELECT
    id,
    code,
    active,
    expired,
    expires_at,
    order_id,
    order_number,
    redeemed,
    type
  FROM giftcards
  WHERE 1=1
  {{ if .id }}
    AND id IN ({{ .id | sqlIntIn }})
  {{ end }}
  {{ if .code }}
    AND code IN ({{ .code | sqlStringIn }})
  {{ end }}
  {{ if .active }}
    AND active = {{ .active }}
  {{ end }}
  {{ if .expired }}
    AND expired = {{ .expired }}
  {{ end }}
  {{ if .expires_at }}
    AND expires_at = {{ .expires_at | sqlDate }}
  {{ end }}
  {{ if .order_id }}
    AND order_id = {{ .order_id }}
  {{ end }}
  {{ if .order_number }}
    AND order_number = '{{ .order_number }}'
  {{ end }}
  {{ if .redeemed }}
    AND redeemed = {{ .redeemed }}
  {{ end }}
  {{ if .type }}
    AND type = '{{ .type }}'
  {{ end }}
  {{ if .codes_like }}
    AND (
      {{ range $index, $code := .codes_like }}
        code LIKE '%{{ $code }}%'
        {{ if not (last $index .codes_like) }}
          OR
        {{ end }}
      {{ end }}
    )
  {{ end }}
  ORDER BY {{ .order_by }}
  {{ if .limit }}
    LIMIT {{ .limit }}
  {{ if .offset }}
    OFFSET {{ .offset }}
  {{ end }}
  {{ end }}


Enter fullscreen mode Exit fullscreen mode

In this template, I have added flags for the different columns in the giftcards table and modified the WHERE clause to include the new flags. I have also added support for the codes_like flag, which takes a list of giftcard codes and generates a filter statement with multiple LIKE queries joined by OR. The order_by flag is used instead of sort_by to specify the order of the results.

We can now of course run this command and benefit from all the cool glazed bells and whistles.



❯ sqleton run-command /tmp/giftcards.yaml --limit 5
+-------+---------------------+--------+---------+---------------------+----------+--------------+----------+----------+
| id    | code                | active | expired | expires_at          | order_id | order_number | redeemed | type     |
+-------+---------------------+--------+---------+---------------------+----------+--------------+----------+----------+
| 22148 | WRHL-3242-KSKD-SZ4Z | 1      | 0       | 2024-04-29 00:00:00 | <nil>    | <nil>        | 0.00     | coupon   |
| 22147 | NHDC-3YF5-2421-VP25 | 1      | 0       | 2024-04-29 00:00:00 | <nil>    | <nil>        | 259.00   | coupon   |
| 22146 | DAB1-1X6Z-K9AV-XXWF | 1      | 0       | 2024-04-29 00:00:00 | <nil>    | <nil>        | 0.00     | warranty |
| 22145 | WFFT-BXEU-6WGT-E559 | 1      | 0       | 2024-04-29 00:00:00 | <nil>    | <nil>        | 99.50    | warranty |
| 22144 | VCCC-FEBP-KP12-U9P3 | 0      | 0       | 2024-04-29 00:00:00 | <nil>    | <nil>        | 0.00     | coupon   |
+-------+---------------------+--------+---------+---------------------+----------+--------------+----------+----------+


Enter fullscreen mode Exit fullscreen mode

Storing and sharing commands

Once you get ahold of such powerful AI programs^W^W^Wcrude word templates, you can stash them in what is called a "repository". A repository is a directory containing YAML files (plans exist to have repositories backed by a database, but that technology is not within our reach yet). The directory structure is mirrored as verb structure in the CLI app (or URL path when deploying as an API), and the individual YAML represent actual commands. These repositories can be configured in the config file as well, as described in the README.

You can also create aliases using the --create-alias NAME flag. The resulting YAML has to be stored under the same verb path as the original command. So, an alias for prompts code php will have to be stored under prompts/code/php/ in one of your repositories.

Let's say that we want to get a rundown of possible unit tests:



❯ pinocchio prompts code professional --use-bullets "Suggest unit tests for the following code. Don't write any test code, but be exhaustive and consider all possible edge cases." --create-alias suggest-unit-tests
name: suggest-unit-tests
aliasFor: professional
flags:
    use-bullets: "true"
arguments:
    - Suggest unit tests for the following code. Don't write any test code, but be exhaustive and consider all possible edge cases.


Enter fullscreen mode Exit fullscreen mode

By storing the result as suggest-unit-test.yaml in prompts/code/professional, we can now easily suggest unit tests:



❯ pinocchio prompts code professional suggest-unit-tests --context /tmp/reverse.go  --concise
- Test with an empty string to ensure the function handles it correctly.
- Test with a single character string to check if the function returns the same character.
- Test with a two-character string to verify the characters are swapped correctly.
- Test with a multi-character string to ensure the string is reversed correctly.
- Test with a string that contains special characters and numbers to ensure they are reversed correctly.
- Test with a string that contains Unicode characters to verify the function handles them correctly.
- Test with a string that contains spaces to ensure they are preserved in the reversed string.
- Test with a string that contains repeated characters to ensure the order is reversed correctly.
- Test with a very long string to check the function's performance and correctness.


Enter fullscreen mode Exit fullscreen mode

Of course, all these commands can themselves be aliased to shorter commands using standard shell aliases.



for i in aws bash emacs go php python rust typescript sql unix professional; do
        alias llm$i="pinocchio prompts code $i"
        alias llm${i}-3.5="pinocchio --openai-engine gpt-3.5-turbo prompts code $i"
done


Enter fullscreen mode Exit fullscreen mode

What does this all mean?

An earth-shattering consequence of this heavenly design is that you can add repositories for various GO GO GADGETS such as sqleton, escuse-me, geppetto or oak to your projects' codebases, point to them in your config file, and BAM, you now have a rich set of CLI tools that is automatically shared across your team and kept in source control right along the rest of your code.

This is especially useful in order to encode custom refactoring or other rote operations (say, scaffolding the nth API glue to import data into your system). Whereas you would have to spend the effort to build a proper AST, AST transformer, output template, you can now write refactoring tools with basically the same effort as writing "well, actually, wouldn't it be nice if…" on slack.

Remember the words that once echoed through these desolate halls:

WHEN LIFE GIVES YOU STYLE GUIDES, DON'T NITPICK IN CODE REVIEWS. MAKE EXECUTABLE STYLE GUIDES! DEMAND TO SEE TECHNOLOGY'S MANAGER! MAKE IT RUE THE DAY WHERE IT GAVE US EXECUTABLE SPEECH! DO YOU KNOW WHO WE ARE? WE ARE THE GO GO GOLEMS THAT ARE GOING TO BURN YOUR CODEBASE DOWN.

This can look as follows, to convert existing classes to property promotion constructors in PHP8.



name: php-property-promotion
short: Generate a class with constructor property promotion
factories:
  openai:
    client:
      timeout: 120
    completion:
      engine: gpt-4
      temperature: 0.2
      max_response_tokens: 1024
      stop:
        - // End Output
      stream: true
flags:
  - name: instructions
    type: string
    help: Additional language specific instructions
  - name: readonly
    type: bool
    default: true
    help: Make the class readonly
arguments:
  - name: input_file
    type: stringFromFile
    help: Input file containing the attribute definitions
    required: true
prompt: |
  Write a {{ if .readonly }}readonly{{end}} PHP class with constructor property promotion for the following fields.

  {{ if .instructions }}{{ .instructions }}{{ end }}

  For example: 

  // Input
  public ?int $productId; // Internal product ID for reference
  public ?string $itemId; // The ID of the item 
  // End Input

  // Output
  public function __construct(
     /** Internal product ID for reference */
     public ?int $productId = null,
     /** The ID of the item */
     public ?string $itemId = null,
  ) {}
  // End Output

  Now create a constructor for the following fields.

  // Input
  {{ .input_file }}
  // End Input

  // Output



Enter fullscreen mode Exit fullscreen mode

This I think is the most exciting aspect of LLMs. They make it possible to build ad-hoc tooling that is able (even if stochastically hitting or missing) to do rote but complex, ill-defined, time-consuming work that is very specific to the problem and situation at hand. I have been using tools like the above to cut through unknown codebases, add unit tests, clean up READMEs, write CLI tools, generate reports, and much more.

The ones I built today are quite useful and make for cool demos, but the real value comes lies in being able to do very fuzzy, ad-hoc work that needs to be repeated at scale.

Where do we go from here?

I hope to make it easier to share and package these custom prompts and slowly start advertising GO GO GOLEMS and its ecosystem more, in order to get community contributions.

A second project that is underway is building agent tooling. Single prompt applications are useful but often suffer from limited context sizes and lack of iteration. I have been working on a "step" abstraction that should make it possible to run complex agent workflows supporting iteration, error handling, user interaction, caching.

A third project underway is a "prompt context manager" to make it easy to augment the LLM applications with additional information, coming either from external documents, live queries against a codebase, external APIs, saved snippets and summaries from past conversations, etc…

Finally, I have a currently closed-source framework that makes it possible to deploy any glazed command (i.e., a single YAML file) as a web API, a lambda function or a WASM plugin. I hope to be able to port this part to opensource, as it makes the tools exponentially more useful.

Top comments (1)

Collapse
 
wesen profile image
Manuel Odendahl

I strongly believe that ad-hoc, custom, personal tools powered by large language models is going to be an important paradigm for future use. What do you think? Do you build your own tools for LLMs instead of just chatting with GPT directly?