Skip to content

shivam93/mind-window

Repository files navigation

Mind Window

Designing how agents think — and how humans watch them think.

Most agent demos show you the output. Mind Window is a study in the other layer: the mind (how an agent decides, recalls, and refuses) and the window (how a person watches that decision happen and chooses to trust it).

Each entry is one agent, built end-to-end, documented with its real traces, its design rationale, and an honest account of where it broke.

🔗 Live: https://shivam93.github.io/mind-window/


Agent 01 — The Article Analyst

An agent that reads what you read, builds a memory of it, and answers questions against the whole corpus — citing the specific source behind every claim, and flagging the claims it can't ground.

  • 3 LangGraph graphs over one SQLite memory: article ingestion, corpus query, autonomous digest
  • 71-article corpus (235 runs deduplicated), 3072-dim embeddings via sqlite-vec
  • Every claim carries a source_typearticle / past_brief / web_search / model_knowledge. model_knowledge is the honest one: "verify me." 18/18 digest citations traceable, 0 orphans.
  • Built across 28 sessions, model: Claude Sonnet 4.6

The moment that matters: mid-run, the agent detects its own web search drifting off-topic, issues a RETRY, and recovers — captured on a real trace (run-019e6027). Resilience caught live is more convincing than a demo that never stumbles.

Read it

Deep dives

  1. Trace as Thinking Map — one real run, drawn as the agent's cognition
  2. Schema Mind — how the output contract shapes the thinking
  3. Decision Architecture — when the model, not the code, picks what happens next
  4. Librarian & Analyst — separating mechanical work from cognitive work
  5. Trust Discipline — "verify me, not trust me" as trust architecture
  6. Empirical Method — how testing, not planning, revealed the design
  7. Design Principles — the extracted laws of agent architecture

The bet behind the studio

  • Judgment is the seat. When generation is free, the value is in the decision the agent makes over messy input — not the text it produces.
  • The window is the design. An agent's behavior under uncertainty — how it hedges, grounds, and refuses — is the whole interface. Making that legible is the work.
  • The failures are the proof. Where an agent breaks, and the tradeoff made when there was no perfect answer, is what separates designed work from a template.

An ongoing agent design study by Shivam Bhatnagar. Built, not generated. All trace data is real — no fabricated outputs.

About

Designing how agents think — and how humans watch them think. An ongoing agent design study.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages