In-Depth: Harishkotra - Detailed Analysis

Harish Kotra (he/him)

Nov 3

I built a video detective that runs on a 2B model and never phones home

#ai #liquidai #programming #dailybuild2026

9 min read

Harish Kotra (he/him)

Nov 3

Two databases, one question: how I built Eligible

#ai #productivity #appwrite #dailybuild2026

10 min read

Harish Kotra (he/him)

Nov 2

Selling a judgement to an agent

#ai #productivity #x402 #dailybuild2026

6 min read

Harish Kotra (he/him)

Nov 1

Can an agent buy from you?

#ai #x402 #productivity #dailybuild2026

6 min read

Harish Kotra (he/him)

Oct 31

I built a napkin that turns scribbles into real diagrams, entirely in the browser

#ai #productivity #programming #dailybuild2026

8 min read

Harish Kotra (he/him)

Oct 30

I tried to test Google's "sleep" paper on a Mac mini

#ai #programming #productivity #dailybuild2026

10 min read

Harish Kotra (he/him)

Oct 29

Two databases, one question: how I built Eligible

#ai #programming #appwrite #dailybuild2026

7 min read

Harish Kotra (he/him)

Oct 28

I built a local photo rescuer in a day, and the hard part was not the model

#ai #desertantlabs #productivity #dailybuild2026

8 min read

Harish Kotra (he/him)

Oct 27

Catchment: answering five questions about a place with one database

#appwritehack #ai #programming #dailybuild2026

8 min read

Harish Kotra (he/him)

Oct 26

I built an oracle that refuses to answer

#ai #programming #productivity #dailybuild2026

7 min read

Harish Kotra (he/him)

Oct 25

The Enforcement Gap: measuring whether a coding agent follows its own rulebook

#ai #programming #productivity #dailybuild2026

1

2

9 min read

Harish Kotra (he/him)

Oct 24

Your coding agent isn't flaky. Its inference server is.

#ai #programming #productivity #dailybuild2026

6 min read

Harish Kotra (he/him)

Oct 23

The CLI is the judge: compiling an org policy into a real `agents-cli` extension

#ai #programming #productivity #dailybuild2026

9 min read

Harish Kotra (he/him)

Oct 22

I put a 740M vision model in a browser tab and finally searched my meme folder

#showdev #ai #machinelearning #webdev

8 min read

Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady Submission 🦥

Harish Kotra (he/him)

Oct 21

Sloth Mode: an agent that does your dread while you do nothing

#devchallenge #hf26challenge #productivity #dailybuild2026

8 min read

Harish Kotra (he/him)

Oct 20

Ask in Telugu, get the answer out of an English insurance policy

#ai #programming #productivity #dailybuild2026

4 min read

Harish Kotra (he/him)

Oct 19

A 2B vision model judged my listing photos. It knew what was wrong and still could not tell me whether to ship them.

#ai #programming #productivity #dailybuild2026

1

5 min read

Harish Kotra (he/him)

Oct 18

The model scored 19 percent, then rewrote its own manual to 100

#ai #programming #productivity #dailybuild2026

8 min read

Harish Kotra (he/him)

Oct 17

I built the smallest version of local semantic search for macOS

#ai #machinelearning #search #swift

12 min read

Harish Kotra (he/him)

Oct 16

Two local decision models play chess, and every probability is on screen

#ai #machinelearning #programming

16 min read

Harish Kotra (he/him)

Oct 15

How I made a small decision model's belief visible, and what that taught me about building honest AI demos.

#ai #programming #productivity #dailybuild2026

7 min read

Harish Kotra (he/him)

Oct 14

Your agent says it addressed the review comments. Here's how you find out if it actually did.

#ai #programming #productivity #dailybuild2026

1

5 min read

Harish Kotra (he/him)

Oct 13

Four AI agents argue over one Penpot canvas until the design is good

#ai #programming #productivity #dailybuild2026

9 min read

Harish Kotra (he/him)

Oct 12

I built an app where you type a sentence and a real, editable design appears on a Penpot canvas

#ai #programming #productivity #dailybuild2026

1

7 min read

Harish Kotra (he/him)

Oct 11

I built the same agent twice to see what a framework actually deletes

#webdev #ai #productivity #dailybuild2026

2

6 min read

Harish Kotra (he/him)

Oct 10

Two agents, two companies, one protocol: building a visible agent-to-agent negotiation

#ai #programming #productivity #dailybuild2026

1

11 min read

Harish Kotra (he/him)

Oct 9

Guardrails are a lie until they're arithmetic

#guardrails #ai #programming #dailybuild2026

1

11 min read

Harish Kotra (he/him)

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

14 min read

Harish Kotra (he/him)

Oct 7

Building Anvil: code-as-action with a capability sandbox that explains its refusals.

#ai #programming #productivity #dailybuild2026

1

8 min read

Harish Kotra (he/him)

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

12 min read

Harish Kotra (he/him)

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

8 min read

Harish Kotra (he/him)

Oct 4

Your agent is a long-running process with side effects. Kill it and watch what happens.

#ai #programming #productivity #dailybuild2026

11 min read

Harish Kotra (he/him)

Oct 3

Sleeptime memory consolidation: an agent that edits its own memory and proves it still remembers

#ai #productivity #programming #dailybuild2026

15 min read

Harish Kotra (he/him)

Oct 2

Luthier: an agent that audits an AI coding agent's harness against the repo it governs.

#ai #productivity #programming #dailybuild2026

9 min read

Harish Kotra (he/him)

Oct 1

Building Clay: an A2UI host where the model emits interface instead of prose

#ai #productivity #programming #dailybuild2026

1

11 min read

Harish Kotra (he/him)

Sep 30

One UI, Any Agent: Proving Framework Independence with AG-UI, Mastra, and React

#ai #productivity #programming #dailybuild2026

5 min read

Harish Kotra (he/him)

Sep 29

Bloom: I Made Two LLMs Paint the Same Sentence and Measured What Happened

#ai #programming #productivity #dailybuild2026

7 min read

Harish Kotra (he/him)

Sep 28

Weave: turning two models' answers into one claim graph

#ai #programming #productivity #dailybuild2026

10 min read

Harish Kotra (he/him)

Sep 27

Proving a Model Upgrade With CSS and a Disabled Script Engine

#ai #programming #productivity #dailybuild2026

6 min read

Harish Kotra (he/him)

Sep 26

Reverb: Making Model Progress Audible - Two LLMs, One Prompt, Eight Seconds of Web Audio

#ai #programming #productivity #dailybuild2026

7 min read

Harish Kotra (he/him)

Sep 25

Graphite: making two LLMs draw their own comparison

#ai #programming #productivity

9 min read

Harish Kotra (he/him)

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

4 min read

Harish Kotra (he/him)

Sep 23

Two models, one prompt, and the checklist that made it worth sharing

#ai #programming #productivity #dailybuild2026

13 min read

Harish Kotra (he/him)

Sep 22

How I built Refract: a live arena where two LLMs fight in GLSL

#ai #programming #productivity #dailybuild2026

1

4 min read

Harish Kotra (he/him)

Sep 21

Which Model Wrote This? — building a game that measures whether you can tell two LLMs apart

#ai #webdev #programming #dailybuild2026

13 min read

Harish Kotra (he/him)

Sep 20

Building "The One-Sentence Torture Test": making LLM comparisons falsifiable

#ai #programming #productivity #dailybuild2026

9 min read

Harish Kotra (he/him)

Sep 19

Building The Confidence Curve

#ai #programming #productivity #dailybuild2026

1

14 min read

Harish Kotra (he/him)

Sep 18

Two Models, One Board: Building "Model vs Model"

#ai #programming #productivity #dailybuild2026

1

16 min read

Harish Kotra (he/him)

Sep 18

Automating LLM A/B Testing: How to Build a Cross-Model Evaluation Harness Programmatically

#ai #programming #productivity #dailybuild2026

6 min read

Harish Kotra (he/him)

Sep 17

I made two LLMs draw the same cat. The constraint is the whole point.

#ai #programming #productivity #dailybuild2026

9 min read

Harish Kotra (he/him)

Sep 16

I measured how deterministic LLMs actually are, prompt by prompt. The results broke my hypothesis.

#ai #programming #productivity #dailybuild2026

1

10 min read

Harish Kotra (he/him)

Sep 15

I built a particle simulator to find out if two AI models are secretly the same model

#ai #programming #productivity #dailybuild2026

11 min read

Harish Kotra (he/him)

Sep 14

I Built a Drag Race for LLMs, and the Loser Is Usually the Better Model

#ai #programming #productivity #dailybuild2026

1

10 min read

Harish Kotra (he/him)

Sep 13

Why Your AI Agents Keep Calling the Wrong Tools (And How We Built Toolsmith to Fix Them)

#ai #programming #productivity #dailybuild2026

6 min read

Harish Kotra (he/him)

Sep 12

Voice Arena: I made two AI voice agents fight live on Agora and let the internet judge

#ai #programming #agora #dailybuild2026

3 min read

Harish Kotra (he/him)

Sep 11

I Scraped All 234 YC Summer 2026 Startups and Found 31 That Are Just a SKILL.md

#ycombinator #dailybuild2026 #ai #programming

2 min read

Harish Kotra (he/him)

Sep 10

Building Prism: a 100%-offline 3D visualizer for your AI coding history

#ai #programming #productivity #dailybuild2026

1

4 min read

Harish Kotra (he/him)

Sep 9

ArchitectGPT: Turning One Sentence Into a Production Architecture Diagram (and a Roast)

#ai #webdev #programming #dailybuild2026

1

5 min read

Harish Kotra (he/him)

Sep 8

I built an AI Dungeon Master in an afternoon — here's the engineering behind it

#ai #programming #productivity #dailybuild2026

1

8 min read

Harish Kotra (he/him)

Sep 7

Building an AI Dungeon Master: A Living Text Adventure with an LLM as the Game Engine

#ai #programming #productivity #dailybuild2026

1

5 min read

AngelHack

Gaia

Want to connect with Harish Kotra (he/him)?