Everything Letterknife does

The homepage covers the three things nobody else can give you. This page is the rest — the full toolkit of a working communications agent across email, calendar, and Slack.

📥Triage that learns you

Four verdicts — important, learn from, not important, archive — applied by rules it learned from you, not filters you had to write.

Sender rules from corrections

Correct one call in plain words and it becomes a durable rule — exceptions included.

Per-sender memory

It remembers how you treat each sender and applies that knowledge only when that sender shows up.

Cold-email ledger

Prospecting mail gets flagged and remembered. One click purges a sender for good.

Bulk unsubscribe

Newsletters you never read get unsubscribed, not just archived.

Learn-from mode

Newsletters worth keeping are harvested into knowledge, then archived — read without reading. And harvesting isn’t limited to newsletters: any email carrying a durable insight — a client sharing what works, an operator changing policy — gets distilled into the knowledge base while the mail is handled normally.

Clean inbox lifecycle

Filed mail stays visible while its task is open, then archives itself when the work is done.

Tasks, asks, and follow-ups

Email is work in disguise. Letterknife makes the work explicit.

Threads become tasks

Every real conversation is tracked as a task with status, history, and a next step.

The ask box

Each task shows what is currently being asked of you — not just the last message.

Goals and chains

Related threads roll up into goals, so pursuing one objective through three people is one item, not three.

Reply reconciliation

It knows when someone replied, when they didn’t, and chases the silence for you.

Waiting, not rotting

When the ball is on their side the task parks as waiting — and reopens by itself the moment a reply lands or its follow-up comes due.

Timed follow-ups

“Chase in a week” is one sentence: the task parks, and when the date hits the agent checks the thread and drafts the nudge if they stayed quiet.

Projects

Tasks group into your projects — a name, keywords, and optionally a working folder, so code tasks run inside the codebase they belong to.

Watch mode

Things others are driving get an eye icon and stay out of your plan until they need you.

First-raised tracking

See when something first came up versus when it last moved — nothing quietly rots.

🗓Today’s Plan

The inbox turned into an operated day.

A morning plan

Calls, replies, approvals and chases assembled into one prioritized list, every day.

Visible time budget

The plan shows how your hours split between calls and desk work before you commit to it.

Live calendar mirror

Meetings sync in near-realtime — moved, cancelled, and declined calls resolve themselves.

Activity rollup

A 24-hour digest of everything the agent did, so unattended never means unaccountable.

Quiet by design

Nothing you did yourself rings the bell — notifications are reserved for what happened while you weren’t looking.

✍️Writing and sending

Drafts in your voice, sent only with your consent.

Drafts in your voice

Replies are written from your history and style — ready before you open the thread.

Starts new emails

Ask it to write someone and it composes a fresh email in your voice — drafted for review, with a follow-up task on the new thread so the reply comes back tracked.

Consent gates

Nothing sends without an explicit OK. Typed conversation never counts as permission.

Attachment handling

It reads image attachments for context, and any attachment opens natively with one click.

Full thread awareness

Drafts account for the whole conversation and the sender’s profile, not just the last message.

Send closes the loop

Sending a draft is treated as your move: the task updates itself — ask cleared, follow-up scheduled, status parked — without another click.

💬Beyond the inbox

One brain across the places work actually happens.

Unlimited Gmail accounts (coming)

Your login is your identity; soon you’ll connect every inbox you own under one plan — work, personal, side project.

Slack merge

Slack conversations flow into the same tasks and plan as email — one thread of truth per topic.

Contact profiles

Every sender gets a profile: open tasks, history, disposition — visible right in the reader.

Bulk people processing

Sweep an entire backlog of senders in one run once the agent knows your preferences.

🎓Learning mode

The onboarding is the training. No forms, no interview.

One email at a time

Resumable training slides: it judges, you correct, it converges — visibly, in one sitting.

Exceptions are first-class

“Usually skip — except my own community” is one correction, captured whole.

Accuracy you can see

A running score of accepted recommendations shows the learning actually happening.

A knowledge base you can read

Everything it learns lands in a knowledge base it curates itself — general knowledge, plus facts about the companies and people you deal with, each surfaced only in the right conversation. Every entry in plain language, editable or deletable in the app, mirrored to plain-text files on your disk. No black box.

Maintains its own memory

On a schedule you pick (daily or weekly), a maintenance chain folds in your recent corrections, audits the whole knowledge base for contradictions and stale facts, dedups what it harvested, and lifts durable facts to where they belong. No gardening required.

🤖Agent-native architecture

Most tools have an API about the product. Letterknife exposes the product itself to your AI.

Your AI drives everything

Every capability — reading, tasks, calendar, sending — is a tool your own Claude can operate.

Show it, don’t describe it

Drop an image or PDF into any task chat and the agent reads it directly.

Usage-aware orchestration

It budgets your Claude subscription like it budgets your time: visible spend, auto-pause, resume.

Local runtime

The agent, its memory, and its rules live on your machine. Close the lid and nothing of yours is anywhere else.

🔐 Security

An assistant that knows your life is a target. Everything Letterknife knows carries a disclosure level, and what unlocks is decided in code from verified sender addresses — never by what an email claims.

Public

General knowledge

Who you are, how you work, reference knowledge it has harvested — everything safe to use in any conversation.

Unlocks for: everyone, always.

Company

Organization facts

Account details at your bank, procedures with your insurer, project state with a client. Family works as a group too.

Unlocks for: mail sent from an address that organization vouches for — double auth: the right person and the right address.

Private

Person facts

What you know about one specific person — history, preferences, the personal record of an ex-colleague or a friend.

Unlocks for: that person only, from their verified addresses.

Impersonators get nothing

“Your broker” writing from a random Gmail address meets an assistant with no account numbers in its context and no tool that will hand them over — the best it can do is draft “I’ll check and get back to you.” Your real broker gets the full picture automatically.

Gated in code, not prompts

What unlocks is decided by verified sender addresses, never by what an email claims — gated facts are never even injected, and the AI can’t widen its own access. Only an instruction you type yourself overrides.

Access expires with the address

When someone leaves a company and their work address is shut down, their access to company info ends with it — their personal record still works, the company’s doesn’t. No revocation list to remember.

Companies are never invented

“I’m from your bank” creates nothing. A new company relationship takes real engagement from you — you actually replied — plus a person who verifiably exists at that company. The impersonator whose “employee” isn’t findable anywhere is caught before anything is created.

Learning is fenced too

The agent can harvest a useful insight from any email — but that write path is restricted in code to adding inert, public-level notes. A malicious email can never use it to alter what the agent knows about you, a company, or a person.

Letterknife-only mode

An optional security mode strips the agent down to Letterknife’s own tools — no filesystem, shell, or web — so a malicious email can never reach your files, your repos, or the wider internet.

The full model — and why it's a guarantee rather than a guideline — is in the security docs.

🚧 On the roadmap

Being honest about what's not here yet:

Mobile approver appMultiple email accountsWhatsAppOutlook supportEnd-to-end encrypted sync across devicesOpen-source core

See it on your own inbox

The feature list is one thing. Watching it learn your mail in twenty minutes is another.

© 2026 Letterknife. The local-first communications agent.