✎ PROWRIT the field guide
THE FIELD GUIDE

What to use when

Six everyday situations, explained at the level that stays true when the tools change: what kind of thing each job needs, where the risk line sits, and what each tier costs you in setup and trust. Specific product picks live only inside the dated boxes — everything outside them should still be true next year.

situations, not tools · capability tiers, not menu paths · dated picks, quarantined · refusals included

A note on the words, since they changed under everyone's feet. What most people still call prompt engineering is now usually split into three: writing the instruction (the prompt), deciding what the model can see while it works (the context), and arranging the steps, checks and retries around it (the harness). The distinction earns its keep — most failures that look like a badly worded prompt are really a step handed the wrong material, or no check at the point where the work could go wrong. Everything below is written at that level, whichever term is current. So is the studio: it designs the material each step receives and the loops that catch it, not only the sentences.

SITUATION 01

“My morning email, checked and summarized.”

The most-wanted automation there is, and the most misunderstood. A chat AI can't see your inbox — something has to connect to it. The whole decision is how much power that connection gets.

BUILT-IN DIGEST your mail app's own AI SCHEDULED TASK chat AI + mail connection AGENT IN THE INBOX can label, file, reply zero setup · their format minutes of setup · your format real power · real risk reads your mail acts on your mail — the consent line

Everything left of the line only produces text. Crossing it is a security decision, not a feature upgrade.

CURRENT PICKS — CHECKED JULY 2026

Live in Google? Gemini's built-in daily brief digests inbox + calendar with zero setup — you just can't choose when it arrives or exactly what it covers.

Want it your way? A scheduled task in ChatGPT (with the Gmail connector) or Claude (tasks now run on their servers — your laptop can sleep) reads mail on a clock and writes the brief to your spec. Claude will draft replies but won't send them — you press send, which is the right default.

Not recommended: giving an autonomous agent your primary mailbox as your first experiment. If you want to try tier 3, use a separate account it can't damage. Also: these run on a clock, not “when mail arrives” — nobody does reliable event triggers in a consumer setup yet.

The brief-writing half is prompt engineering, and it's already done: see the Daily Assistant in the library — or paste your own version into the studio.

SITUATION 02

“Meeting notes that don't miss the decisions.”

Recording is solved; that's not the problem. The problem is that a generic summary gives you topics, when what you need is decisions, owners, and deadlines — and that somebody in the room has to be told a bot is listening.

PLATFORM RECORDER built into your meeting app NOTETAKER APP joins or listens alongside EXTRACTION PASS transcript → your contract IT-approved · generic notes better structure · visible bot works with ANY recorder your own tools something others can see — the visibility line

Tier 3 isn't a product — it's a prompt you run on the transcript afterwards. It upgrades whichever recorder you already have.

CURRENT PICKS — CHECKED JULY 2026

Default: your meeting platform's built-in recorder + summary — it's the one your IT already allows, and tier 3 fixes its blandness anyway.

If you're free to choose: the dedicated notetakers are genuinely better at speakers and action items; pick any established one and spend your attention on the extraction pass instead.

Not recommended: sending a bot into a client call without asking first, and paying for a premium notetaker while still reading generic topic summaries — the upgrade you're missing is the prompt, not the plan.

The extraction pass is exactly what Meeting Accountability in the library does — decisions, owners, deadlines, and a check that none got invented.

SITUATION 03

“An inbox that triages itself.”

The trap in this one is specific: many AI tools can categorize your mail brilliantly — in their own window — and still can't touch a single label in your actual inbox. People discover this after setup, not before.

RULES & FILTERS no AI — and still underrated AI-ASSISTED READING summaries, priority views WRITE-ACCESS AGENT labels, files, drafts for real deterministic · free read-only · your inbox untouched rare in consumer setups reads writes — the consent line

“Can it label?” is the question that separates tier 2 from tier 3 — ask it before connecting anything.

CURRENT PICKS — CHECKED JULY 2026

The honest state of the art: a fully self-maintaining triage in a personal setup is still mostly a build, not a purchase. The combination that actually works today: boring mail rules for the predictable 80%, plus a scheduled AI brief (situation 01) for the residue.

Not recommended: anything marketed as “inbox autopilot” for your primary account — the demos are real, the failure modes (mis-filed client mail, auto-replies you didn't see) are also real, and you won't notice them until they've been happening for a while.

The triage logic itself — what counts as urgent, what gets what label, in what order — is engineered in Inbox Triage in the library; it runs in any chat AI on a pasted batch today.

SITUATION 04

“A research digest, on a schedule, to my taste.”

The safest situation in this guide — nothing here touches your accounts. The quality difference is entirely in the spec: what sources count, what counts as news, and what the digest must refuse to do when there's nothing worth saying.

HUMAN CURATION newsletters, editors SCHEDULED DIGEST chat AI, on a clock, your spec DEEP-RESEARCH RUN 20+ min browsing dossier highest signal per minute unattended · verify the links occasional · often capped a habit a project — the attention line

Tier 2 is a daily habit; tier 3 is for the week you're making a decision. Mixing them up wastes either your quota or your mornings.

CURRENT PICKS — CHECKED JULY 2026

Tier 2 today: scheduled tasks in any of the major chat AIs do this well now; pick the one you already pay for. Demand linked sources in the output — it makes padding visible.

Tier 3 today: every major AI has a deep-research mode; they're genuinely good and rate-limited enough that you'll naturally save them for real questions.

Not recommended: replacing your two best human-curated newsletters with an AI digest — editors still beat scrapers on signal; the digest's job is covering what your niche needs that no editor covers.

The spec is the product here — paste “every Monday I need…” into the studio and it engineers the source rules, the inclusion bar, and the honest-when-empty clause for you.

SITUATION 05

“Should I run an autonomous agent?” (the OpenClaw question)

The honest answer most guides won't give: it depends on which side of a terminal you live on. In 2026 these are still not consumer products — including the famous one — however capable they genuinely are.

CHAT answers you COPILOT SESSION acts while you watch AUTONOMOUS AGENT acts while you sleep zero risk confirms before it commits you own the security boundary supervised unattended — the supervision line

OpenClaw lives entirely right of the line: your machine, your accounts, any model, its own schedules and memory. That's the appeal and the risk in one sentence.

CURRENT PICKS — CHECKED JULY 2026

Comfortable in a terminal, curious, separate accounts? Self-hosted OpenClaw is the most interesting software you'll run this year. Give it a fresh email and phone number, not your real ones, and treat community skills like unsigned browser extensions.

Want the taste without the ops? Managed hosting ($15–60/mo) has become the middle path — they handle the sandboxing and updates; the injection risk is reduced, not eliminated.

Not recommended: self-hosting if the command line isn't home for you — the project's own maintainer says the same. And no agent, hosted or not, gets your primary email, banking, or client data in 2026. That's not caution; that's the current measured state of agent security.

Whichever agent you run, it learns jobs through skill files — and every Prowrit workflow exports as SKILL.md, the open format these agents install. Engineer the job here, hand the skill to your agent.

SITUATION 06

“Answers from my own documents — not the internet.”

Contracts, research PDFs, your own notes: the job is getting answers grounded in your material, with the AI forbidden to improvise. The tiers differ by how much of your world the tool can see.

PASTE & ASK one-off, in any chat PROJECT WITH FILES a persistent set, cited answers CONNECTED DRIVE your whole workspace, searchable zero setup · a book fits the sweet spot for most people an access decision, not a feature files you chose everything you have — the access line

Modern contexts fit a book's worth of text in one go — for a single document, tier 1 plus good instructions beats any fancy setup.

CURRENT PICKS — CHECKED JULY 2026

For a living set of documents: notebook-style tools (grounded, citation-first by design) and the project features of the major chat AIs both do this well now; pick by where your documents already live.

Not recommended: uploading client-confidential files to a personal AI account because the enterprise approval was slow — the convenience is real and so is the liability.

Synthesizing across MANY documents is its own craft — see the Interview Distiller for the multi-document pattern, or engineer your own extraction contract in the studio.

How this page stays honest: everything outside the dashed boxes is written at capability level — no product picks, no menu paths — so provider redesigns can't rot it. The dashed boxes are re-checked quarterly, every stamp updated even when nothing changed: “checked, still true” is the point. Something here wrong or newly stale? The next restamp will say so, in public.