# letmereviewyourcode

> Zishan Ali Khan builds agentic AI systems for institutions where autonomous failure is a legal event, then publishes the review: field guides, episodes, and the numbers.

Author: Zishan Ali Khan (Enterprise AI GTM & Solutions, Camunda; Toronto / New York)
LinkedIn: https://linkedin.com/in/zishanalikhan
GitHub: https://github.com/letmereviewyourcode

Every document below is also available as raw markdown by appending `.md` to its URL.
MCP server (Streamable HTTP, stateless): POST https://zishanalikhan.com/api/mcp — tools: list_documents, get_document, search_documents.
Full content index (JSON with markdown bodies): https://zishanalikhan.com/content-index.json
Translations: available under /fr/, /es/, /hi/, /zh/ (machine-translated; English is canonical).

## Field guides (reference-grade documents)

- [AG-UI: Streaming the Interface, Not Just the Answer](https://zishanalikhan.com/guides/agui-field-guide/): A field guide to AG-UI, the agent-to-user event protocol: event anatomy, transports, process-orchestrated generative UI, and what it leaves unsolved.
- [AP2: The Agent Payments Protocol](https://zishanalikhan.com/guides/ap2-field-guide/): A builder's deep dive into AP2 v0.2: mandate cryptography, the four-party model, threat model, and Human-Not-Present flows, verified against the spec.
- [Where Agents Actually Work: Field Notes from 50+ Enterprise Builds](https://zishanalikhan.com/guides/where-agents-work/): Field notes from 50+ enterprise agentic AI builds: where agents earn their keep, by industry and workflow shape, and where plain code still wins.
- [The Control Plane: Governing Agentic AI at Scale](https://zishanalikhan.com/guides/governing-agentic-ai/): Agent frameworks own the inner loop. Your institution owns the outer one. A framework-agnostic pattern for governing agentic AI in production.
- [Evaluating Agentic Systems: The Four-Axis Method](https://zishanalikhan.com/guides/evaluating-agentic-systems/): A field-tested method for evaluating process-embedded AI agents: cost per case, per-field accuracy, tool-skip rates, and temperature sensitivity.
- [Tool Contracts: Why Agents Skip Your Tools](https://zishanalikhan.com/guides/tool-contracts/): Why agents silently skip tools: a failure taxonomy, the spec rules that measurably cut skip rates, and a deterministic 0-100 linter for MCP tool contracts.
- [A2A: Agent-to-Agent, a Field Guide for Builders](https://zishanalikhan.com/guides/a2a-field-guide/): A builder's field guide to the A2A protocol: Agent Cards, task lifecycle, orchestration vs swarm, privacy boundaries, and the threat model that matters.

## Writing

- [Your agents inherit your data residency](https://zishanalikhan.com/writing/sovereign-agents/): If your data cannot leave the country, neither can your agents' reasoning. Notes on the sovereign-AI constraint most multi-agent architectures assume away.
- [The model was fine. The tool spec was the bug.](https://zishanalikhan.com/writing/agents-skip-tools/): An eval finding that changed how I write tool descriptions: agents skip tools because of specs, not capability. The fix is a contract, not a bigger model.
- [Agent payments: mandates, not trust](https://zishanalikhan.com/series/agents-orchestrated/agent-payments/): AP2 v0.2 plus Camunda 8: signed mandates, a DMN spending policy outside the model, and an audit trail for every hop of an agent-initiated payment.
- [AG-UI: the agent that streams an interface, not a transcript](https://zishanalikhan.com/series/agents-orchestrated/ag-ui/): AG-UI streamed from a Camunda 8 backend: generative cards, tool calls, and human approvals in one BPMN process, with the audit trail for free.
- [Loops: the agentic primitive everything converged on](https://zishanalikhan.com/series/agents-orchestrated/loops/): Every major agentic coding tool converged on the same loop primitive. The moat is not the loop. It is the verification step, and who can audit it.

## Other pages

- [About](https://zishanalikhan.com/about/): who Zishan is, the record, how he works
- [Work](https://zishanalikhan.com/work/): public builds and reference implementations
- [Talks](https://zishanalikhan.com/talks/): speaking history
- [Now](https://zishanalikhan.com/now/): what he is building right now