Automations Worth Building First
A sort key for your automation backlog from running scheduled agents in production: script it, agent it, or leave it a checklist -- plus three failure modes.
· 6 min read
AI Knowledge Work
AI tools for PMs, analysts, and knowledge workers — what actually saves hours, tested against the hype.
19 articles
Writing an AI Usage Policy Your Team Will Actually Follow
Ban lists fail. Classify data instead: three tiers, a fast approval path, one accountability rule, and a versioned doc with an exceptions log.
· 6 min read
The AI Pilot That Never Ships
AI pilots rarely fail outright; they stall in an extension loop with no exit criteria. What production asks that a demo never does, and how to pass it.
· 7 min read
AI Adoption Without a Mandate: Rolling Out AI Tools
No budget, no policy, no executive email. Pick one workflow, keep honest receipts, and handle the three ways adoption stalls.
· 6 min read
AI Translation and Localization QA: A 3-Tier Pipeline
Deterministic CI checks, an LLM review pass, and sampled human review, with a scoring model that survives an argument. Staffable by real teams in 2026.
· 7 min read
Claude Skills for Product Teams: Packaging a Workflow
Turn a workflow only one person can run into a shared Skill: folder structure, writing the description, review process, and the failure modes.
· 6 min read
AI for Stakeholder Updates: A One-Page Sprint Summary
Sort the sprint into four buckets, constrain the prompt, then check the draft for invented causality, status inflation, and flattened severity.
· 6 min read
AI Agents for Code Review and Knowledge Sharing
AI coding agents can act as a first-pass code reviewer and knowledge capture tool. Here is how teams are using them without replacing human judgment.
· 6 min read
AI Coding Agents for Data Analysis Workflows
OpenCode and similar agents can write scripts, clean data, and build charts. Where they help analysts, and where human judgment is still required.
· 6 min read
OpenCode for Documentation and Technical Writing Teams
Technical writers and documentation teams can use OpenCode to extract API changes, update code examples, and keep docs in sync with the codebase.
· 6 min read
OpenCode for Technical PMs: Review Code Without Writing It
OpenCode's terminal agent explains diffs, traces changes, and answers codebase questions without replacing your engineers' workflow.
· 6 min read
Terminal AI Agents for Non-Coding Technical Tasks
AI coding agents are not just for writing code. They can write scripts, query logs, and automate terminal tasks that technical workers deal with every day.
· 6 min read
Perplexity vs ChatGPT Search: Citations for Analysts, 2026
We chased every claim back to its source in both tools. Here's how their citation workflows differ and which one to trust.
· 7 min read
AI Tools for Turning Messy Notes Into Decisions in 2026
Capture is solved; synthesis isn't. We compare tools that turn scattered meeting notes, voice memos, and docs into something you can act on.
· 7 min read
Using AI to Draft PRDs Without Losing the Plot
A step-by-step process for product requirements documents: what to feed the model, what to keep human, and where drafts quietly drift off course.
· 7 min read
AI Meeting Notetakers: Granola, Fathom, Otter in 2026
We compared how they capture meetings, what they cost, and which workflow each one actually fits.
· 7 min read
NotebookLM vs ChatGPT Projects for Research Work in 2026
Source handling, citations, and drift compared side by side, plus which tool fits which research job.
· 8 min read
Using AI to Synthesize User Research Interviews
A 2026 workflow for turning transcripts into themes: where it saves hours, where it hallucinates, and how to keep findings traceable.
· 7 min read
Notion AI for PMs in 2026: What Actually Saves Time
A PM's honest review: where Notion AI replaces real work, where it produces convincing-but-useless output, and what turns $10/month into hours saved.
· 7 min read