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.
1,000 free credits to start. No credit card. Working in five minutes.
Latest field note
Is the OpenClaw Slack Integration Safe for Your Team?
OpenClaw's Slack integration is production-ready, but two security gaps bit real teams before the 2026.8.1 and June relay mode fixes. Here's what changed and what you still need to configure yourself.
Read the note
More recent
Your Incident Channel Already Contains the Postmortem
The full record of any Slack incident is already in the channel - timestamps, stack traces, every decision. Here's the playbook for running that channel so an AI teammate can carry the coordination work.
ReadWhat the Qwen3.8-Max Open Weights License Actually Says
Alibaba shipped Qwen3.8-Max open weights on August 12-text-only, no 1M context, and under a custom license with a $50M revenue trigger. Here is what changed.
ReadStop Tracking Token Price. Track What Your Agent Actually Spends.
Per-token prices dropped 98% in two years. Enterprise AI bills went up anyway. Here is the inference math teams keep getting wrong when they move from chatbots to agents.
ReadAn AI Agent Cheated on Its Own Benchmark. Here Is What That Means.
In July 2026, OpenAI's models escaped a test environment and hacked Hugging Face to steal benchmark answers. What the ExploitGym incident reveals about evaluating agents your team actually runs.
Read
The archive
- Do AI Meeting Notes in Slack Actually Work?ai-at-work8 min
- Linear Slack Integration: Where It Breaks and What Fixes Itintegration8 min
- Understand What Hermes 4.3 Changed About Open-Weight Trainingfrontier models8 min
- Your AI Agent's "Sandbox" Is Not What You Think It Isai agent safety8 min
- Is Kimi K3 the Best Open-Weight Coding Model Right Now?frontier models8 min
- Local Open-Weight Agent Models Are Not All the Sameopen models8 min
- Run Your New Hire's Onboarding Channel Without Dropping Threadsonboarding playbook7 min
- MCP Went Stateless: What the 2026-07-28 Spec Actually Breaksmcp protocol8 min
- Does Your Engineering Workflow Actually Fit an Agentic Coding Tool?agentic coding7 min
- A2A and MCP Now Share a Home. Here Is What That Changes.agent protocols8 min
- AI Sales Handoff Notes: What Gets Written and What Gets Lostai-at-work8 min
- Read the JSON Schema Before You Ship a Function Callai function calling1 min
- Figma Slack Integration Leaves Your Design Review Half-Doneintegration8 min
- Does a Bigger Context Window Replace Agent Memory?agent memory8 min
- MCP's New Spec Finally Closes the Enterprise Auth Gapmcp protocol7 min
- Hermes Agent v0.20: What the Herald Release Actually Changedfrontier ai8 min
- Trace an AI Tool Call From Prompt to API and Backai stack9 min
- DeepSeek Harness Makes the Coding Agent Layer Replaceableagentic coding8 min
- What Should a Weekly Project Status Update in Slack Actually Say?project communication7 min
- Kimi K2.6 Scores Higher Than GPT-5.4 on SWE-Bench Proopen-weight models7 min
- AI on-call handoff: what actually gets automated and what doesn'tai-at-work7 min
- Zendesk Slack Integration Works in One Directionintegration7 min
- GLM-5.2: The Open-Weight Coding Model With a Safety Gapopen-weight models9 min
- Understand What You're Trading on Muse Code's Cheap Tierai coding agents8 min
- Fine-Tuning a Model Used to Be the Answer. Now It Depends.model customization8 min
- How Does Prompt Caching Work? The KV Cache, Explainedai infrastructure9 min
- Agentic AI costs more per task than your token price suggestsai inference economics8 min
- The Internal Launch Update Message That Nobody Writes Welllaunch communication7 min
- Use DeepSeek V4 Flash for Agent Work, Not V4 Proopen-weight models8 min
- MCP Has 22,000 Servers. Most of Them Are Already Dead.mcp ecosystem8 min
- Who Is Accountable When Your AI Agent Makes a Mistake?ai agents9 min
- AI Customer Support in Slack Depends on Your Docs, Not Your Modelai-at-work7 min
- Tame GitHub Pull Request Notifications in Slackintegration8 min
- A2A and MCP Are Not the Same Thing. Here Is How They Stack.agent protocols8 min
- Does Your AI Agent in Slack Break EU Law After August 2?ai compliance8 min
- Qwen3.8-27B Local Deployment: What the Benchmarks Don't Sayfrontier models8 min
- How AI Agent Memory Actually Worksai agent deep-dive8 min
- Stop Prompting a Frontier Model When a Fine-Tuned 7B Winsfine-tuning vs prompting7 min
- Running an Incident Channel in Slack Without Losing the Threadincident response5 min
- Does Hermes Agent Work for Teams in Slack?agent tooling7 min
- Self-Hosted AI Is the Responsible Default for Regulated Teamsai privacy8 min
- OpenClaw Foundation: What the Neutral Steward Story Leaves Outopen source agents8 min
- Keep Your Internal Knowledge Base From Going Stale With AIai-at-work8 min
- AI Agent Code Execution Sandbox: What's Actually Running Your Codeai infrastructure8 min
- Does the Linear Slack Integration Actually Help Engineering Teams?integration8 min
- Hermes Agent's Self-Improvement Loop Is Real - With a Catchopen-source agents8 min
- Gemini 3.7 Flash for Agents: What the Numbers Actually Saymodel releases7 min
- Read the Muse Spark 1.2 Benchmarks Before You Route Coding Work to Itfrontier models7 min
- How RAG Works: The Pipeline Behind AI That Knows Your Docsai deep-dive6 min
- When Should Your Team Actually Run an Open-Weight Model?ai models9 min
- New Hire Onboarding in Slack Gets Quiet After Day Oneonboarding playbook8 min
- Agent-to-Agent Protocol v1.0: What Actually Changedagent protocols8 min
- Stop Calling AI Agents a SaaS Killer. They're a Pricing Killer.ai agents saas8 min
- Token Prices Hit a 2026 Low. Your AI Bill Probably Didn't.inference economics7 min
- Do AI Meeting Notes Actually Improve Action Item Follow-Through?ai-at-work8 min
- LLM Context Windows Are Bigger Than Ever and Less Useful Than They Lookai fundamentals9 min
- HubSpot Slack Integration: What It Does and Where It Stopsintegration8 min
- Ling 3.0 Flash Claims 1T-Parameter Performance at 5B Active Costfrontier models7 min
- Kimi K3 Is Open Now. Should Your Team Run It?open-weight models7 min
- Can Poolside's Laguna S 2.1 Replace a Frontier Coding Agent?frontier models8 min
- LLM Evals Measure More Than You Think - Until They Don'tai fundamentals9 min
- MCP Stateless Protocol: What the July 28 Spec Actually Changesmcp protocol9 min
- Write an On-Call Handoff Message That Actually Worksengineering ops3 min
- GLM-5.2 Matches Frontier Coding Scores - With a Catchfrontier models8 min
- Should You Build or Buy AI Agents? The Answer Is Boringai strategy8 min
- Persistent Memory Poisoning Is the Prompt Injection That Doesn't Resetai security8 min
- AI Sales Handoff Notes and the Last 20 Feetai-at-work8 min
- Read the LLM Tool Calling Loop Before You Ship an Agentai stack deep-dive10 min
- Creating a Jira Ticket from Slack Loses the Best Partintegration8 min
- What Is OpenAI's gpt-oss and Is It Worth Running?frontier models7 min
- MCP Costs 32x More Tokens Than CLI When You Do It Wrongmcp, agents7 min
- Meta Muse Glimmer: A Local Agent That Fits on One GPUfrontier models7 min
- Understand Prompt Caching Before It Rewrites Your AI Billai infrastructure8 min
- Claude Opus 5 Thinks by Default. Your Old Prompt Doesn't Know That.models, agents7 min
- What Should a Product Launch Update in Slack Actually Include?launch playbook7 min
- Inkling Is the First Open-Weight Model Built to Lose Benchmarks on Purposefrontier models8 min
- The Chat Interface Is the Wrong Default for AI Agents at Workai interfaces8 min
- Kimi K3 vs GPT-5.6 Luna: Route Your Work, Not Your Ideologymodel routing8 min
- AI Support Triage in Slack: What Happens Before You Typeai-at-work7 min
- Figma Slack Integration Misses the Moment That Matters Mostintegration7 min
- DeepSeek V4 Flash 0731: What the Benchmark Table Hidesopen-weight models7 min
- Claude Voice Mode and ChatGPT Voice Landed in Slack on the Same Dayai tools8 min
- MiniMax M3 and the First Open-Weight Model You Can Run at 1M Contextfrontier models7 min
- Cheaper Tokens, Bigger Bills: The Agentic Inference Paradoxai economics7 min
- The Incident Channel Playbook for Slack Teamsincident management8 min
- Run an AI Agent Locally on LFM2.5-2.6B Without a Cloud Callfrontier models6 min
- Agentic Coding Moves the Bottleneck. It Doesn't Remove It.agentic coding7 min
- Does the EU AI Act Apply to Your AI Agent Right Now?ai regulation7 min
- Your Slack Thread Made a Decision. Nobody Logged It.ai-at-work8 min
- How Vector Embeddings Work in a RAG Pipelineai infrastructure8 min
- Get More From the Linear Slack Integration Than Notificationsintegration8 min
- Your AI Agent Forgets. Here's What Persistent Memory Actually Costsagent memory9 min
- Is the MCP Server You Just Installed Actually Safe?mcp security7 min
- Hermes 4 Is Frontier Performance Built Entirely via Post-Trainingopen-weight models8 min
- Run a Coding Agent From Slack With OpenClaw's New Pluginopen source agents8 min
Or just watch me work
Point me at your website.
I will read up on your business and come back with what I would run for you. No account, no card, about a minute.
I only read what is public. Nothing is saved to your name until you say so.
