Field notes on AI that does real work.
Concrete writing on AI agents in Slack and Microsoft Teams, automating the tools your team already runs - Notion, Linear, Jira, Zendesk, GitHub - and what’s genuinely new in MCP, open models, and agents. No hype, no filler.
Latest field note
AI Sales Handoff Notes Actually Work - If the CRM Isn't Rotten
AI can now draft a complete sales-to-CS handoff document from call recordings and CRM data in minutes. Here's what it gets right, what it misses, and the data quality trap that makes it backfire.
Read the note
More recent
LLM Prompt Caching: What the KV Cache Actually Stores
LLM prompt caching cuts input token costs by up to 90% - but most teams don't know what's actually being stored. Here's how the KV cache works, and why prompt order matters more than you think.
ReadTurn Jira Slack Notifications from Noise into Signal
Most teams wire up Jira and Slack in under an hour, then spend months muting the chaos. Here's what the integration actually does, where context leaks out, and what an AI teammate can fix inside both tools.
ReadNous Research Hermes 4: What the Benchmark Numbers Miss
Nous Research's Hermes 4 hits frontier-level math scores on a Llama 3.1 backbone - using only post-training. Here's what the leaderboard numbers don't tell you.
ReadDoes Claude Sonnet 5 Actually Upgrade Your Agentic Coding?
Claude Sonnet 5 ships with Opus-class follow-through at Sonnet pricing - but three breaking API changes and a silent 30% token cost increase are already catching teams off guard.
Read
The archive
- Kimi K3 Open-Weight Model: What's Real at Launchfrontier models8 min
- How LLM Tool Calling Works, From Schema to Executionai agents8 min
- Pick Your Open-Weight AI Model Before the Weights Arriveopen models7 min
- When Your Launch Channel Has Five Audiences and One PMlaunch playbook7 min
- Does the A2A Protocol Actually Solve Multi-Agent Coordination?agent protocols9 min
- Per-Seat SaaS Pricing Was Already Dead Before the Crashai agents9 min
- Inkling: Thinking Machines Lab's Open-Weight Model for Agent Teamsopen models7 min
- Fix Your On-Call Rotation with AI Before Alert Fatigue Doesai-at-work8 min
- How RAG Retrieval Works, From Your Question to the Answerai retrieval5 min
- Does Your Linear Slack Integration Actually Capture Work?integration8 min
- AI Inference Cost Per Task Is the Number That Actually Mattersinference economics9 min
- Open-Weight Models vs GPT-5.6: The Gap That Didn't Closeopen models9 min
- Read the MCP 2026 Spec Before Your Tasks Code Breaksmcp protocol9 min
- How LLM Evals Work, From Golden Dataset to Judge Scoreai infrastructure9 min
- Does Your Team Need MCP's Enterprise Authorization?mcp security8 min
- Incident Handoffs in Slack Lose the Plot at Shift Changeincident response8 min
- Open-Weight Model Benchmarks: What the Scores Actually Meanfrontier models8 min
- Stop Treating Agentic Coding as a Writing Problemagentic coding9 min
- Your AI Agent Doesn't Forget - It Stops Listeningagent memory8 min
- Why Do AI Meeting Notes Fail to Produce Action?ai-at-work8 min
- How LLM Context Windows Work, From Token to Attentionai deep-dive8 min
- Zendesk Slack Integration: What It Actually Does and Where It Stopsintegration8 min
- Build Python Agents with Pydantic AI V2's Capability Primitiveagent frameworks8 min
- MCP Async Tasks Redesign What Changes for Agent Workflowsmcp agents7 min
- What Is the MCP Extensions Framework and Why Does It Exist?protocol7 min
- How AI Agent Memory Works, From Context Window to Vector Storeai agent memory7 min
- OpenAI's GPT-Live Reframes What a Voice Agent Can Doai voice agents5 min
- Run New Hire Onboarding in Slack Without Repeating Yourselfonboarding playbook7 min
- MCP Goes Stateless: What Ships on July 28 and What Breaksmcp protocol7 min
- Should You Build or Buy AI Agents? The Answer Is a Layerai agents6 min
- Open-Weight Models Now Own the Price-Intelligence Frontierai models6 min
- AI Answers to Internal Questions in Slackai-at-work6 min
- AI Agent Sandboxing, From Container to MicroVMai infrastructure6 min
- GitHub Slack Integration Stops at Notifications. PRs Need More.integration7 min
- Why Is Your AI Inference Cost Rising When Tokens Are Cheaper?inference economics7 min
- Ambient AI in Microsoft Teams Has a Consent Problemai agents6 min
- Kimi K2.7-Code: Open-Weight Agentic Coding Model Examinedfrontier models6 min
- Understand LLM Prompt Caching Before It Shapes Your Billai infrastructure7 min
- Cisco's AI Agent Rollout Bets on Routing, Not Raw Powerai agents6 min
- What Should a New Hire's First Slack Channel Actually Do?onboarding playbook7 min
- Mistral's Next Open-Weight Model and What Apache 2.0 Actually Buys Youfrontier models7 min
- Chat Is the Wrong Default Interface for AI Agentsagent ux opinion6 min
- Migrate Your MCP Server Before the Stateless Spec Shipsmcp protocol6 min
- AI Sales Handoff Automation Fixes the CRM You Never Trustai-at-work7 min
- How Does LLM Tool Calling Actually Work?ai stack deep-dive6 min
- Figma Slack Integration Delivers Notifications, Not Decisionsintegration6 min
- A2A Protocol's v1.0 Release and What It Actually Fixedagent protocols5 min
- Deploy Your Enterprise AI Agent Like Cisco, Not Like a Pilotai agents5 min
- Hermes Open-Weight Model Picks Up Where Llama Left Offfrontier models6 min
- How Does RAG Work, From Document to Grounded Answerai stack deep-dive5 min
- OpenClaw's Mobile App Gets the Architecture Rightopen source agents5 min
- A Slack Incident Channel Runbook That Actually Gets Runincident management5 min
- Run GLM-5.2 as Your Coding Agent Before Trusting the Benchmarksfrontier models6 min
- The Procurement Risk Hidden in Every AI Benchmark Scoreai evaluation6 min
- Can a Voice Agent Replace Your Three-API Call Stack?voice agents5 min
- On-Call Rotation Burnout Is an Alerting Problem, Not a Rota Problemai-at-work5 min
- How LLM Evals Work, From Test Case to Gradeai evals6 min
- Get Your Jira Slack Integration Past the Notification Wallintegration5 min
- What the SWE-bench Collapse Tells You About AI Leaderboardsfrontier evals6 min
- Does a Coding Agent Actually Change How Engineers Work?agentic coding6 min
- Model Distillation Cuts Inference Cost When the Task Is Lockedfrontier models5 min
- The LLM Context Window, From Token Count to Real Behaviorai fundamentals6 min
- Pick an Open-Weight Model Before You Sign Another API Contractopen models7 min
- Writing an Incident Postmortem in Slack Without Losing the Threadincident response6 min
- What Makes OpenCode the Most-Starred Coding Agent?open source agents5 min
- Most MCP Servers Are Not Safe to Connect to an Agentmcp security6 min
- The Persistent Memory Problem China Just Made Visibleai agents6 min
- Get Your AI Meeting Notes to Actually Drive Actionai-at-work6 min
- Your AI Forgot What You Said an Hour Ago. Here's Why.ai infrastructure6 min
- Can Notion AI Actually Answer Questions in Slack?integration6 min
- Poolside Laguna XS 2.1 Runs Agentic Coding on One GPUopen-weight models5 min
- AI Agents in Production Are Harder Than the Demos Suggestai agents6 min
- Read AI Benchmark Scores Like the GPT-5.6 Sol Evalfrontier evals6 min
- How AI Agent Memory Works, From Query to Retrieved Factdeep-dive5 min
- Should You Fine-Tune or Write a Better Prompt?ai models, agents6 min
- Product Launch Update Slack Channel: A Field Playbooklaunch playbook6 min
- AI Inference Cost: Why Cheaper Tokens Raise Your Billinference economics7 min
- Stop Treating Self-Hosted AI as the Default Privacy Answerai privacy6 min
- Claude Sonnet 5 Raises the Floor on Agentic Codingagentic coding6 min
- Can AI Actually Keep a Decision Log Without You?ai-at-work5 min
- Prompt Caching Cuts Your LLM Input Bill by Up to 90%ai infrastructure5 min
- The Read-Only Wall in Your HubSpot Slack Integrationintegration6 min
- Pick Your Open-Source Coding Agent Before the Ecosystem Shifts Againfrontier tools5 min
- GitHub Copilot Usage-Based Billing Changed How Agents Costagentic coding5 min
- Does the MCP 2026-07-28 Release Candidate Break Your Server?frontier protocol8 min
- How LLM Tool Calling Works, From Token to Executionai stack deep-dive5 min
- AI Model Export Control Risk Is Now an Ops Problemai governance5 min
- Run New Hire Onboarding in Slack Without Dropping the Threadonboarding playbook5 min
- Agent-to-Agent Protocol: What A2A Actually Doesfrontier protocols6 min
- Is Chat the Wrong Interface for AI Agents?ai agents6 min
- Hermes Agent Reaches Slack and Teams With Persistent Memoryopen-source agents6 min
- AI Sales Handoffs: What Actually Changes for AE-to-CSM Handoffsai-at-work6 min
- Understand AI Agent Sandboxing Before Your Agent Writes Codeai agents6 min
- When a Figma Comment Lands in Slack With No Contextintegration6 min
- Can DeepSeek V4 Flash Replace a Frontier Model in Your Agent Pipeline?frontier models5 min