Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
AI, engineering & what survives production Series' Articles
Back to Richard Atkins's Series
Stop shipping AI agents you can't measure: evals + observability from scratch
Richard Atkins
Richard Atkins
Richard Atkins
Follow
Jul 18
Stop shipping AI agents you can't measure: evals + observability from scratch
#
ai
#
llm
#
testing
#
machinelearning
9
reactions
Comments
Add Comment
5 min read
The real economics of a production LLM pipeline: resumability, cost-aware routing, and measuring when local beats the API
Richard Atkins
Richard Atkins
Richard Atkins
Follow
Jul 18
The real economics of a production LLM pipeline: resumability, cost-aware routing, and measuring when local beats the API
#
llm
#
dataengineering
#
python
#
ai
8
reactions
Comments
Add Comment
7 min read
Measure your own coding habits before you believe anyone else's numbers
Richard Atkins
Richard Atkins
Richard Atkins
Follow
Aug 5
Measure your own coding habits before you believe anyone else's numbers
#
git
#
analytics
#
productivity
#
codequality
Comments
Add Comment
8 min read
The code that hides the evidence
Richard Atkins
Richard Atkins
Richard Atkins
Follow
Aug 5
The code that hides the evidence
#
software
#
analytics
#
code
#
devex
5
reactions
Comments
Add Comment
7 min read
An MCP server that has to prove itself: citations, abstention and entitlements as CI gates
Richard Atkins
Richard Atkins
Richard Atkins
Follow
Aug 30
An MCP server that has to prove itself: citations, abstention and entitlements as CI gates
#
ai
#
llm
#
mcp
#
python
Comments
2
comments
5 min read
The migration the data ordered: moving a production LLM pipeline off the Mac Mini under my desk
Richard Atkins
Richard Atkins
Richard Atkins
Follow
Aug 31
The migration the data ordered: moving a production LLM pipeline off the Mac Mini under my desk
#
ai
#
llm
#
cloudnative
#
infrastructure
Comments
Add Comment
5 min read
One LLM judge is an opinion. Two model families agreeing is evidence.
Richard Atkins
Richard Atkins
Richard Atkins
Follow
Sep 2
One LLM judge is an opinion. Two model families agreeing is evidence.
#
ai
#
llm
#
testing
#
machinelearning
Comments
Add Comment
4 min read
Measurement tools need evals too
Richard Atkins
Richard Atkins
Richard Atkins
Follow
Sep 3
Measurement tools need evals too
Comments
Add Comment
6 min read
Earned Autonomy
Richard Atkins
Richard Atkins
Richard Atkins
Follow
Sep 9
Earned Autonomy
#
ai
#
agents
#
automation
#
architecture
5
reactions
Comments
Add Comment
23 min read
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account