Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
dailybuild2026
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Two agents, two companies, one protocol: building a visible agent-to-agent negotiation
Harish Kotra (he/him)
Harish Kotra (he/him)
Harish Kotra (he/him)
Follow
Oct 10
Two agents, two companies, one protocol: building a visible agent-to-agent negotiation
#
ai
#
programming
#
productivity
#
dailybuild2026
Comments
1
 comment
11 min read
Building a Rubik's Cube Decision Arena with 6 Decision Models (Laya, Clef, GLiNER 2.5, Kev and Strands Decider)
Harish Kotra (he/him)
Harish Kotra (he/him)
Harish Kotra (he/him)
Follow
Oct 8
Building a Rubik's Cube Decision Arena with 6 Decision Models (Laya, Clef, GLiNER 2.5, Kev and Strands Decider)
#
ai
#
programming
#
productivity
#
dailybuild2026
Comments
Add Comment
14 min read
Building Anvil: code-as-action with a capability sandbox that explains its refusals.
Harish Kotra (he/him)
Harish Kotra (he/him)
Harish Kotra (he/him)
Follow
Oct 7
Building Anvil: code-as-action with a capability sandbox that explains its refusals.
#
ai
#
programming
#
productivity
#
dailybuild2026
1
 reaction
Comments
Add Comment
8 min read
How Arbiter works, why it was built, and the four measurements it made about an LLM judge that I had to look at twice.
Harish Kotra (he/him)
Harish Kotra (he/him)
Harish Kotra (he/him)
Follow
Oct 6
How Arbiter works, why it was built, and the four measurements it made about an LLM judge that I had to look at twice.
#
ai
#
programming
#
productivity
#
dailybuild2026
Comments
Add Comment
12 min read
How I built a time-travel debugger for LLM agents on Burr, and what "replay the unchanged branch and prove nothing changed" actually takes.
Harish Kotra (he/him)
Harish Kotra (he/him)
Harish Kotra (he/him)
Follow
Oct 5
How I built a time-travel debugger for LLM agents on Burr, and what "replay the unchanged branch and prove nothing changed" actually takes.
#
ai
#
programming
#
productivity
#
dailybuild2026
Comments
Add Comment
8 min read
Guardrails are a lie until they're arithmetic
Harish Kotra (he/him)
Harish Kotra (he/him)
Harish Kotra (he/him)
Follow
Oct 9
Guardrails are a lie until they're arithmetic
#
guardrails
#
ai
#
programming
#
dailybuild2026
1
 reaction
Comments
1
 comment
11 min read
Your agent is a long-running process with side effects. Kill it and watch what happens.
Harish Kotra (he/him)
Harish Kotra (he/him)
Harish Kotra (he/him)
Follow
Oct 4
Your agent is a long-running process with side effects. Kill it and watch what happens.
#
ai
#
programming
#
productivity
#
dailybuild2026
Comments
Add Comment
11 min read
Sleeptime memory consolidation: an agent that edits its own memory and proves it still remembers
Harish Kotra (he/him)
Harish Kotra (he/him)
Harish Kotra (he/him)
Follow
Oct 3
Sleeptime memory consolidation: an agent that edits its own memory and proves it still remembers
#
ai
#
productivity
#
programming
#
dailybuild2026
Comments
Add Comment
15 min read
Luthier: an agent that audits an AI coding agent's harness against the repo it governs.
Harish Kotra (he/him)
Harish Kotra (he/him)
Harish Kotra (he/him)
Follow
Oct 2
Luthier: an agent that audits an AI coding agent's harness against the repo it governs.
#
ai
#
productivity
#
programming
#
dailybuild2026
Comments
Add Comment
9 min read
One UI, Any Agent: Proving Framework Independence with AG-UI, Mastra, and React
Harish Kotra (he/him)
Harish Kotra (he/him)
Harish Kotra (he/him)
Follow
Sep 30
One UI, Any Agent: Proving Framework Independence with AG-UI, Mastra, and React
#
ai
#
productivity
#
programming
#
dailybuild2026
Comments
Add Comment
5 min read
Bloom: I Made Two LLMs Paint the Same Sentence and Measured What Happened
Harish Kotra (he/him)
Harish Kotra (he/him)
Harish Kotra (he/him)
Follow
Sep 29
Bloom: I Made Two LLMs Paint the Same Sentence and Measured What Happened
#
ai
#
programming
#
productivity
#
dailybuild2026
Comments
Add Comment
7 min read
Glyph: I made two AI models fight inside real terminals and the only honest judge is a PTY
Harish Kotra (he/him)
Harish Kotra (he/him)
Harish Kotra (he/him)
Follow
Sep 24
Glyph: I made two AI models fight inside real terminals and the only honest judge is a PTY
#
ai
#
programming
#
productivity
#
dailybuild2026
1
 reaction
Comments
Add Comment
4 min read
Building The Confidence Curve
Harish Kotra (he/him)
Harish Kotra (he/him)
Harish Kotra (he/him)
Follow
Sep 19
Building The Confidence Curve
#
ai
#
programming
#
productivity
#
dailybuild2026
1
 reaction
Comments
Add Comment
14 min read
Automating LLM A/B Testing: How to Build a Cross-Model Evaluation Harness Programmatically
Harish Kotra (he/him)
Harish Kotra (he/him)
Harish Kotra (he/him)
Follow
Sep 18
Automating LLM A/B Testing: How to Build a Cross-Model Evaluation Harness Programmatically
#
ai
#
programming
#
productivity
#
dailybuild2026
Comments
Add Comment
6 min read
How I built Refract: a live arena where two LLMs fight in GLSL
Harish Kotra (he/him)
Harish Kotra (he/him)
Harish Kotra (he/him)
Follow
Sep 22
How I built Refract: a live arena where two LLMs fight in GLSL
#
ai
#
programming
#
productivity
#
dailybuild2026
1
 reaction
Comments
Add Comment
4 min read
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account
