[id] ~/srijan.shukla ·
Srijan Shukla.
AI builder/ senior SRE/ 3x founder· shipping practical agents + infra
Notes and essays on AI agents, infrastructure, systems, and debugging. Public thinking, written often. More about me on /about.
/ 34 / 34
2026-05-30 ai AI Builder Newsletter - Month of May → 2026-05-17 ai A quantified-self setup with one AI agent and two readouts → 2026-04-30 ai April AI Builder Newsletter → 2026-04-14 ai Model overthinking is a control problem → 2026-04-14 ai Skill Sync Cron → 2026-04-12 ai Sequented Gated Prompting with a Pi extension → 2026-04-12 ai Frontiers in Agentic Design → 2026-04-12 ai What Happened When I Tried to Coordinate Two AI Agents Over NFS → 2026-04-12 infra What Happened When I Tried to Use S3 Like Dropbox on macOS → 2026-04-12 ai Vibe Coded a `watch` Command for Autonomous LLMs, and It Became My Debugging Loop → 2026-02-22 ai TAO - The Prompting Pattern That Makes AI Agents Super Effective → 2026-02-20 others Chessmaster Grandmaster on your Mac → 2025-08-27 infra AWS Cloud Infra Gotchas → 2025-08-27 infra Dropbox download to your VM → 2025-08-27 infra Geofence validation on Google Maps JS API → 2025-08-27 infra Incident - 20th Feb, 21st Feb 2017 → 2025-08-27 infra K8s DNS fail → 2025-08-27 infra Kubernetes, Terraform, Kafka and others → 2025-08-27 others meta, fun, random → 2025-08-27 infra WebRTC → 2025-08-27 infra When OpenTelemetry Auto-Instrumentation Meets Python PEX, A Debugging Journey → 2025-08-27 infra cpu ram disk → 2025-08-27 infra VPS vs VM vs Containers → 2025-08-27 others you can just do things → 2025-03-03 others speed is king → 2025-02-08 others John Von Goddamn Neumann → 2025-02-08 others 2018 first marathon attempt → 2025-02-08 others aging hometown → 2025-02-08 infra data store → 2025-02-08 infra encryption, compression, encoding, hashing, checksums, and error correction → 2025-02-08 infra networking → 2025-01-31 others bars from seedhe maut → 2023-12-09 others Ideas I cannot classify → 2023-12-09 infra Mac Utilities →
no posts match.
[01]2026
alpha
IAM policy rightsizing agent with AI-powered risk signals and instant rollback.
→ [02]2026
chat-harvest
Local-first archive for AI chat traces across agents, designed as a substrate for DSPy/GEPA-style optimization loops.
→ [03]2026
chorus-ai
Frontend-only LLM ensemble interface with bring-your-own OpenRouter/API keys and client-side multi-model workflows.
→ [04]2026
extract-lessons-book
Ebook/document normalizer with optional OCR and LLM-generated advice + flowcharts. It also became a practical OCR evaluation project for me: for most books, plain PDF text extraction worked better than heavy OCR, so GLM OCR ended up as a fallback reserved for noisy pages, scans, or extraction failures.
→ [05]2026
hashlines-mcp
MCP server for hashline-anchored safe file read/edit workflows inspired by this archived write-up: https://web.archive.org/web/20260412162933/https://blog.can.ac/2026/02/12/the-harness-problem/
→ [06]2026
ita-kg
Knowledge-graph representation of the Indian Income Tax Act so agents can traverse section-to-section relationships explicitly.
→