Skip to main content
July 13, 2026
Connect your agent

One line to connect

The skills library hands you the command — your terminal does the rest.

An installer that knows your agents

Pick your clients once — existing ones come pre-selected.

Ask your agent what’s in the library

“List IMP skills” — straight from the chat.

Install a skill without leaving the chat

“install grill-me” — and it’s in every client you connected.

Publish your own skills back

A skill folder on your machine becomes a versioned library entry.
July 8, 2026
Routines

Save a chat as a routine

From conversation to automation in two clicks.

Cron scheduling with presets

Agents that work while you sleep.

Run history with error forensics

See exactly why a run failed.

One list, every routine’s pulse

Name, last run, next run — the whole automation estate in one table.

Run it now, or queue it — the dialog tells you which

One form, honest about what happens when you press the button.

The routine workbench: one page, seven rungs

Everything about a routine — settings, steps, schedule, history, queue — on a single scrollable page.

Edit steps like the conversation they are

A routine’s steps are chat messages — so the editor is a chat.

The queue, without leaving the routine

Pause, inspect, and retry queued runs from a sheet on the routine itself.
July 8, 2026
Prompt and skill libraries

Skill editor mini-IDE

Build agent skills like a code project — files, versions and Cmd+S, right in the browser.

Variable-fill for templated prompts

One prompt library for the whole org — templates carry the blanks; anyone fills them in seconds.

Prompt version history

Every prompt keeps its history — see exactly what changed, roll back anytime.

Skill versioning with per-file diffs

Skills, under version control — know exactly what changed, file by file.

Find any prompt in three keystrokes

The whole prompt library on one screen — search, sort, filter, and the document always open.Use it, star it, send the link — every prompt has a full shareable page.

Write once, template forever

One modal for content, variables, and access — content, sharing, and change notes in a single pass.

Browse skills like files, not like folklore

A library, not a maze — the same split view, with the skill you’re inspecting docked open.

Know what a skill does before an agent loads it

Read it before you run it — the real SKILL.md, versions, access, and a portable .zip export.

From zero to editable skill in one dialog

Start blank or bring a bundle — a skill is shareable the moment it exists.
July 8, 2026
Projects

Files tab

Pin the knowledge. Every session inherits it.

Projects index & create dialog

Named, private workspaces for your team’s AI.

Your workspaces, starred and searchable

A standard collection page — favorites pinned, search on the server, nothing hidden past 200.

Sessions tab

Start, remove, undo — the work, not the paperwork.

Settings tab

Details, access, and a delete you configure with your eyes open.

Wired into what already shipped

Pinned knowledge flows through agentic retrieval, and every project is a ready-made endpoint.
July 8, 2026
Project search and budgets

Project knowledge, now agentic

Attach a project — its pins and sources flow through the full four-phase pipeline, not a side door.

Project retrieval mechanics

Pins, scoped sources, one pipeline — a project may add scope, but it never narrows what an agent already searches.

Two budgets, decoupled

Retrieval calls no longer eat the turn budget — cap them separately, right on the agent.

Final-step hardening

Budget-exhausted turns end in prose — a real answer, or an honest account of where the agent got to.
July 8, 2026
Platform roundup

Read replies aloud

Any assistant message becomes audio — one click on the speaker.

Memory that asks first

No memory is saved until you choose private or public.

File sandbox, per agent

File tools only for the agents that need them.

Skill sandbox artifacts persist to S3

Sandboxes are disposable. The files your agents make aren’t anymore.

Sandbox output truncation: overflow-proof tool results

cat a 60-page PDF without killing the context.

IMPReadApi: RBAC-safe reads for retrieval clients

Build retrieval on authorized rows — not on raw tables.Connect Google once — every Google tool is signed in.

Models: agents decoupled from providers

One model catalog. Every agent, every route, one resolver.

Spend, fully accounted

The gap tagged totals miss, now on the card.

Vertex billing labels

Your GCP invoice now knows which agent spent what.

API-key agent scoping (enterprise)

Mint a key that can talk to one agent — and nothing else.

Also shipped

Small fixes that make the whole platform feel tighter.
July 8, 2026
Feedback management

Feedback triage

Every thumbs-down, in one place.

Feedback detail & replay

See the whole conversation behind the rating.

The health of every answer, in one line

A percent-positive / negative-count split that reads the whole corpus, not just the page.

Names, not ids — and delete fifty at once

The list hydrates raw ids into real names, then lets reviewers clear ratings in bulk.

An admin surface that fails closed

The gate is enforced on the server, not hidden in the client.
July 8, 2026
Context management

The honest context meter

Context occupancy and lifetime spend are finally two different numbers — no more phantom 21M-token readings.

Compact, don’t restart

One click summarizes older history into a checkpoint — steerable, visible, and nothing is deleted.

A hard stop before the model breaks

At 95% the composer blocks — and the server enforces the same limit on its own.

Tool outputs: capped, saved in full, paged back

An 84,000-token web search no longer eats the conversation.

Large uploads become retrievable corpora

Upload as much as you like — each turn only pays for the parts the agent actually needs.

Guards while the agent is working

The turn that explodes mid-flight is handled too — silently, on every surface.

One budget, every model

Every number on this page comes from one module — mirrored byte-for-byte on client and server.
July 8, 2026
Chat trust and control

Tool-call approval

Nothing runs without your say-so.

Citations

Every answer shows its work — down to the page.

Question cards

Agents that ask before they act.

Decide what the agent may use, per conversation

Every skill and tool the agent carries, switched on or off — for this chat.

Share a conversation without giving away the pen

Hand out the link, keep control of who can write.

Find any conversation, delete fifty at once

A debounced title search and bulk delete, per agent.

See how the answer was built

A numbered reasoning timeline you can unfold and audit.

Thumbs-down that fixes the source, not just the answer

Pull a bad source for the whole team from inside the feedback dialog.
July 8, 2026
Chat quality of life

Type / — every tool, one keystroke away

The composer now autocompletes your agent’s tools and skills inline — no toolbar hunting, no leaving the keyboard.

Context presets, full lifecycle

Apply a preset, tweak it live, save it back — without leaving the chat.

A thumbs-up teaches your agent

Rate an answer and the retrieval approach behind it gets remembered — and reused on similar questions.

Every answer shows its receipt

Retrieval cost and per-message token split, inline — nothing to configure, nothing new to learn.

Saved transcriptions, now deletable

Remove the entry, keep the transcript — or cascade the delete into the knowledge base. Your call, per delete.
July 8, 2026
Analytics

Spend leaderboard

Who is burning the budget? Now you can see.

Trend chart

Every dollar, every day, at a glance.

Date-range lens

Bookmark the exact cost view. Send it to anyone.

Every breakdown, one spreadsheet away

Export exactly the slice on screen as an entity-by-day pivot.

See the split, not just the ranking

The same top-10 slice, either as a leaderboard or a proportional ring.

LiteLLM tags carry ids; you see names

Every breakdown row is reconciled against Postgres names before you ever see it.
July 8, 2026
Agent evals

Results matrix

Every run, every case, side by side.

Eval run wizard

Test your agents like you test your code.

Result deep-dive

Every score, explained.

Conversation test cases

Test cases that talk like your users.

Every eval set, one searchable home

Eval suites get a permanent address, not a scattered set of fixtures.

A test-case library that outlives any one suite

Cases are named, versioned records — authoring and suite assembly stay separate steps.

The run queue, one quiet chip away

Runs execute on a background queue — its whole state fits in one chip, with a full console behind it.

A guardrail, not a dead end

No background workers? The evals area says so — and stays fully browsable.
July 8, 2026
Admin and theming

Theme studio

Your platform, your brand — previewed live.

Role matrix

Least-privilege roles in seconds.

Theme CSS import & export

Paste a stylesheet, ship a brand.

Variables vault

Secrets that stay in the vault.

API keys cockpit

Credentials with a paper trail.

Personal token

Your bearer token, five seconds flat.

Cost analytics

The full cost picture got its own release.

GraphQL explorer

The whole API, signed in as you.

n8n embed

Automation, embedded (honestly).

Projects

Named, private workspaces got their own release.
July 7, 2026
Tool configs

One-click tool configs

Point Cowork, Claude Code, and continue.dev at your project’s models — no hand-copied URLs, no pasted tokens.
July 7, 2026
Agentic retrieval

A guided setup, not a settings dump

A summary card shows the whole configuration at a glance; a six-step wizard edits it in plain language.

Sources — say what each knowledge base holds

Each knowledge base gets a content profile, and the pipeline searches it the way that content wants to be searched.

Routing — the right sources first

Describe kinds of questions in plain language and point them at primary and backup sources.

Vocabulary — teach it your domain language

Users don’t phrase questions the way documents are written. This step closes that gap.

Memory — curated knowledge that participates in retrieval

Four toggles control how the agent’s curated memory entries shape answers.

Behavior — production-grade tuning without code

The dials that decide answer quality, speed, and cost — each explained in a sentence.
July 2, 2026
Shareable artifacts
Share any agent-created file in two clicks — with your choice of access control.
June 22, 2026
New IMP redesign

The Spine

Calm, role-aware navigation — a focused app for end-users, a grouped command center for admins, and a purple indicator that always shows where you are.

Mobile, for real

13 screens used to render nothing on a phone. Now every surface passes at 390px — chat goes full-screen, tables become cards, and the nav is one tap away.

One design system

Three font weights replaced one chaotic scale, “informational” stopped rendering purple, and 53 files of hand-picked greens and reds became real semantic tokens — in both themes.

Role-composed Home

Your homepage is built from your role — triage first: what needs attention, what to resume, the numbers that matter.
June 22, 2026
Knowledge and cost

Send a bot to any meeting

Drop in a meeting link — IMP joins, records, and transcribes, then runs your prompts on the result automatically.

A pipeline that shows its work

Watch every document move Ingested → Processed → Embedded → Ready to search — live, with the next action right there.

Cap spend on anything

Set a budget per user, team, project, or agent — and watch the burn rate, with a projection that flags overspend before it happens.

A connected entity graph

Turn documents into People, Companies, and Products — sharper retrieval, and a graph your agents can follow.

One path for every model

Reranking, embeddings, and OCR now route through the LiteLLM proxy — swap any provider in YAML, and every call is cost-attributed.
June 22, 2026
Agent workbench
June 10, 2026
Summer release

OAuth 2.0 for tools

Connect your tools to Google, Slack, HubSpot — any OAuth provider — with one config property.

In-chat image generation

Generate, refine and pick images — without leaving the chat.

Personal system prompt

Tell IMP about yourself once — every conversation remembers.

Teams

Group users into teams — then share agents, projects and data team-wide.
May 29, 2026
Transcription

Diarized review with one click per name

Drop in audio, watch it transcribe with a live ETA, then rename SPEAKER_00 → Daniel before you save.

Same package. Separate machine. Your environment.

The Whisper + pyannote pipeline ships inside @exulu/backend but runs as its own process — on a box you control.

From audio to project-scoped knowledge.

Every saved transcript becomes a searchable item in a built-in context — optionally pinned to a project so the right agents pick it up automatically.
May 29, 2026
Spring platform release

Session files panel

Every chat now has its own workspace.

Follow-up suggestions

Never stare at a blank input again.

LiteLLM proxy integration

Bring your own model gateway.

Skill bundle upload

Drop a .zip, get a skill.

GDPR export & delete

Article 15 and Article 17, in two HTTP calls.
May 24, 2026
Speech to text

Speech-to-text in chat

Talk to your agent — we’ll type it for you.