How it works

How Launchpad works

A workspace for your team, rooms for each project, sessions where AI coworkers do the work, and memory that keeps it all in place.

Coworkers

Each coworker has a role, instructions, knowledge, tools and a model.

Rooms

Rooms keep each project’s people, context and knowledge together.

Sessions

A session puts you and your coworkers around one goal, with its own working memory.

Ways of working

Sessions can run in different ways: you lead, a coworker leads, the team talks it through, or a set process runs.

Memory

Memory has a scope. Rooms keep project context together.

How we protect your work →

A useful insight from one session passes a review, is saved to the room, and is curated into the team playbook.

It gets better

Good ideas move up into your playbook, approved by you.

Three ways to add a coworker: talk it through, bring your current AI, or build one from scratch.

Start in minutes.

Launchpad Live from $29/month incl. VAT

Start Launchpad Livefrom $29/month incl. VATTry the demoFree recorded demo · No live AI calls

Going deeper

The full system, for evaluators

How information moves, what persists, where review happens, and what is enforced rather than promised — section by section.

1. System overview

Your team defines its AI coworkers, teams and ways of working once. Each project can have its own room within the workspace, where those coworkers work with that project’s context in structured sessions, and the results become deliverables through two canvases: the editable Report Canvas and the polished, recipient-facing Design Canvas.

Your organisation’s workspace — specialists, teams and shared methodology

Client delivery room A

Project room — scoped access

Client context & firm methodology
Knowledge library — documents, notes, decisions
Delivery team of AI specialists
Lead · specialists · critic · validator
Structured working sessions
The team works the question together
Report Canvas → Design Canvas
Editable report → polished deliverable

↓ Client-ready deliverable — PDF export or email

Client delivery room B

Project room — scoped access

Client context & firm methodology
Knowledge library — documents, notes, decisions
Delivery team of AI specialists
Lead · specialists · critic · validator
Structured working sessions
The team works the question together
Report Canvas → Design Canvas
Editable report → polished deliverable

↓ Client-ready deliverable — PDF export or email

Each engagement can use a room within the workspace with the same structure: context in, the specialist team works and reviews, a deliverable comes out. Room access and content permissions govern who may use the material.

The four moves you actually perform to build the system:

Create a coworker
Give your coworker a real identity — who they are, what they know, and what they should never let slide. Defined once, consistent every time.
Assemble a team
Choose who is in the room, assign roles, and set the ground rules. The team frame keeps each coworker in character.
Run a session
Submit a prompt and the team takes it from there — exchanging context, handing off to each other, and producing a result together.
Save a canvas
The result lands in a structured, editable canvas. Refine it, reshape it, and share something real.

The product overview walks the full feature set behind this page.

2. Client context

Everything a specialist knows about a client arrives through paths you control:

Where client information lives: In the project room within your workspace: uploaded documents, sessions, transcripts and attachments are kept with the work. Workspace and team knowledge can also be made available to authorised members.
What is loaded into a session: The prompt, the team configuration, each specialist’s definition, and relevant knowledge and memory retrieved for the question at hand — retrieval is query-time and selective, not a bulk dump of the whole library into every call.
What persists after a session: The session record, canvases and scoped durable memories are separate stores. Some low-authority observations can be saved automatically; portable personal memories and protected rules require human approval.
How information is scoped: Knowledge and memory carry an access scope as well as their workspace and room containment. Scope and the caller’s permissions govern which material may be used; a room is not a separate memory scope.
What remains private: Use room access and content permissions to choose the audience for project material. Workspace knowledge can serve several rooms for authorised members; a guest does not gain workspace-wide access by entering a room.

3. AI specialists

A specialist — Launchpad calls them coworkers — is a durable role, not a throwaway prompt. Its definition carries a purpose and expertise, working instructions (including what it should always challenge), access to knowledge and tools, its own scoped memory, and a model configuration from the platform’s model catalog.

The durable definition lets you reuse a specialist’s craft across engagements. Keep client material in the appropriate room, and review knowledge or memories attached to a reusable specialist before making them available to a new audience.

4. Delivery teams

Roles and lead behaviour: A team assigns roles: a lead runs the working session and hands off to the right specialist; specialists contribute their own angle rather than talking over each other.
Critic and validator: Two review roles are first-class: the critic challenges assumptions and reasoning; the validator sorts claims into supported, unsupported and unresolved. They are teammates in the session, not an afterthought.
Collaboration rules: How the team interacts — turn-taking, hand-offs, how much challenge is expected — is set on the team, so each specialist stays in character while the team decides how they work together.
Output requirements: A team can be pointed at an output: the session works toward a concrete artifact — a diagnosis, a memo, a roadmap — rather than an open-ended conversation.

5. Sessions

How a session begins: You choose the team and submit a real prompt — the question, the task, the deliverable to work toward.
How context is assembled: The runtime assembles each specialist’s working context from its definition, the team frame, and the knowledge and memory relevant to the prompt (section 2).
How specialists contribute: The conversation is structured: the lead directs, specialists contribute in role, the critic and validator review as the work develops — visibly, in the transcript.
How tools are used: Specialists invoke capabilities mid-session — long-document analysis, contract review, web research, design and image generation, even building a new teammate — with the results landing in the session.
When your input is requested: The session can pause for you: a specialist can ask for a decision, a clarification, or missing material, and continue once you answer.
How the working output develops and the session ends: Useful material accumulates as the session runs; when the work is done you carry the result into a canvas (section 6) — the session stays as the record of how the result was reached.

6. Working material, Report Canvas, Design Canvas

Launchpad separates three kinds of material, and the separation is the quality model:

Raw findings and working material: The session transcript, tool results and drafts — the workshop floor. Useful, inspectable, and deliberately not the deliverable.
Report Canvas — the curated working report: A block-based, editable document with version history. You restructure, rewrite and cut; this is where human judgment is applied to the work.
Design Canvas — the recipient-facing deliverable: Generated from the Report Canvas you shaped: a polished, styled document ready for the client — exported as a PDF from the browser or sent by email.

AI working material never automatically becomes a client deliverable — the path runs through a report you edited and approved.

7. Validation and approval

The critic and validator give every engagement structured challenge: assumptions are questioned in the open, and claims are sorted by whether the evidence supports them. That is review support — it is not a truth guarantee, and Launchpad does not claim one. What requires human review is, deliberately, everything that reaches a client: the consultancy edits the report, approves the deliverable, and remains responsible for the final output.

Formal pre-delivery review gates — an enforced sign-off step with an approval record — are in development and not yet part of the live product; today the review discipline is the workflow above.

8. Memory and reusable knowledge

Short-term session context: The session’s current goal, constraints and progress are carried in working context. This is distinct from durable memory and is not a complete replay of the transcript.
Durable memory: Access scope and containment determine who may use a memory; authority distinguishes a rule, guidance or observation. Protected rules and reusable shared learning require human review; some low-authority observations can be saved automatically.
Personal memory and coworker learning: Portable personal memories require your approval. A coworker can also automatically retain screened professional observations about you, limited to you, that coworker and the workspace where you worked together. You can turn future learning off in Settings; doing so does not remove memories already saved.
Selective recall: Coworkers can draw on saved memories across sessions. Recall selects a limited amount of relevant context and can miss a saved fact, so confirm important constraints in the current brief.
Client-scoped knowledge: The engagement’s documents and context belong with its project room, within the workspace. Their scope and permissions determine who may use them.
Team-scoped knowledge and firm methodology: Method material attached where it belongs — to a team, or to the workspace as the firm’s way of working.
Approved promotion of reusable learning: Moving learning between teams is a deliberate act: approved team knowledge can be copied to another team, and specialist/team definitions are reusable assets. What is live today is exactly that — human-controlled copy and reuse. A one-click “promote to firm IP” pipeline is a direction, not a shipped feature.

Screening helps identify sensitive or client-specific material, but it can make mistakes. Review a proposed lesson and its intended readers before making it shared knowledge.

9. Tools and integrations

Specialists work with real capabilities inside a session: web research, long-document analysis, contract review, multi-format document design, image generation, and in-session builders that create a new specialist or team. Integrations connect outside systems: Fortnox is live today — reads during a session, writes only after your explicit approval. We name integrations only once they are live.

10. Security architecture

Workspace isolation & row-level security: Database row-level security and permission checks govern workspace, room and content access.
Role-based permissions: Workspace roles decide what each member can see and do.
Credential handling: Upstream credentials are held in a managed vault by reference — never stored in plaintext rows, never returned to a client.
Governed memory & approval-gated writes: Memory follows the scope/authority rules in section 8; integration writes wait for explicit human approval.
Data export and deletion: Data export and account deletion controls are available inside the product. Account deletion and archiving a memory are different actions; an archive removes a memory from active use and is not proof that every retained copy has been erased. Retention and data rights are described in the Privacy Policy.

The complete technical and policy explanation — including the sub-processor register — is on the Security & trust page.

11. Technical FAQ

Straight answers, kept in step with the implemented product — where something isn’t live yet, the answer says so. Pricing details live on the pricing page.

Which AI models does Launchpad use?
Launchpad works with models from multiple leading AI providers, managed through a platform model catalog. Every AI call — conversation, document analysis, embeddings, design generation — runs through one managed gateway, which applies the same credential handling, metering and security posture regardless of provider. The catalog evolves as providers do, so we don’t pin model names here.
Can different specialists use different models?
Yes. Each AI specialist (coworker) carries its own model configuration from the catalog, so a research-heavy specialist and a drafting specialist on the same delivery team can run on different models.
How is context selected for a session?
A session assembles context from your prompt, the team configuration, each specialist’s definition, and knowledge and memory available for the current work. Coworkers can draw on saved memories across sessions. Recall selects a limited amount of relevant context and can miss a saved fact, so confirm important constraints in the current brief.
Is client data mixed between workspaces?
A workspace is the tenant boundary; rooms organise projects inside it. Database access controls, room access and content scopes govern which material may be used. Workspace-level knowledge can serve several rooms for authorised members, while a guest’s room access does not grant workspace-wide access.
What becomes long-term memory?
Access scope and containment determine who may use a memory; authority distinguishes a rule, guidance or observation. Protected rules and reusable shared learning require human review; some low-authority observations can be saved automatically. Screening helps identify sensitive or client-specific material, but it can make mistakes. Review a proposed lesson and its intended readers before making it shared knowledge.
Can users approve or reject memory?
You can approve or reject proposed memories and manage saved memories in Settings. Portable personal memories require your approval. A coworker can also automatically retain screened professional observations about you, limited to you, that coworker and the workspace where you worked together. You can turn future learning off in Settings; doing so does not remove memories already saved.
Can outputs be edited manually?
Yes — that is the point of the Report Canvas. It is a block-based, editable document with version history: restructure sections, rewrite passages, delete what you disagree with. The polished Design Canvas is generated from the report you shaped, not from the raw session.
How are PDFs and designed outputs produced?
The Report Canvas can be turned into a Design Canvas — a polished, styled, client-facing document produced by a dedicated design worker. You can export a PDF directly from your browser, or send the deliverable by email from the workspace.
Can clients view an output without entering the workspace?
Today, delivery happens on your terms: export a PDF or send the deliverable by email — your client never needs a Launchpad account. Self-serve recipient view links are in development and will be announced when they work end to end, not before.
What integrations are currently supported?
Fortnox is the live integration today: specialists can read from it during a session, and any write waits for your explicit approval. More connectors are planned — we only name integrations that are live.
What is stored by Launchpad?
Your workspace content: specialist and team definitions, sessions and their transcripts, uploaded knowledge documents, governed memories, and your Report and Design Canvases. Data export and account deletion controls are available inside the product. Account deletion and archiving a memory are different actions; an archive removes a memory from active use and is not proof that every retained copy has been erased. Retention and data rights are described in the Privacy Policy. The full security posture — including the sub-processor register — is on the Security & trust page.
How are AI and tool costs metered?
Every AI call runs through one gateway that meters real usage against the workspace’s balance. Subscription plans include capacity, and Launchpad is a paid product — a workspace needs an active plan to run AI work. Current plans are on the pricing page.
Can a consultancy create several client workspaces?
Yes. An account can belong to several workspaces, each with its own subscription. Rooms within a workspace organise client projects without creating a new tenant or subscription. Consultancy-level portfolio billing across workspaces is not yet live.
Can methodology be reused between clients?
Yes. Specialist and team definitions are reusable assets, and approved team knowledge can be copied into another team when you choose to. Keep client material in its project room and review the scope and readers before sharing a lesson. Screening helps identify sensitive or client-specific material, but it can make mistakes. Review a proposed lesson and its intended readers before making it shared knowledge.
Which capabilities are live, and which are planned?
Live today: isolated workspaces with row-level security, durable AI specialists and delivery teams with critic and validator roles, structured working sessions, scoped knowledge and governed memory, the editable Report Canvas with versions, Design Canvas generation, email delivery, browser PDF export, the Fortnox integration, and a security audit log. In development (not yet claimable end to end): client-facing share links, engagement-led onboarding, consultancy portfolio billing, and pre-delivery review gates. This answer is reviewed as the product evolves.

The current state

The work is already spread across more places than the deliverable shows.

The proposal is somewhere. Discovery is in transcripts and notes. The method lives partly in documents and partly in experience. Useful reasoning sits in AI conversations. New client decisions arrive through meetings. Senior feedback changes the answer again. Before the next piece of work can move, someone has to reconnect what matters.

The point is not that this workflow is broken. It works, because good consultants repeatedly reconstruct the right conditions for good work. Launchpad is designed to reduce how much of that reconstruction has to happen again and again.

The operating change

Keep the method reusable. Keep the client context with the client.

Launchpad separates two things that are easy to blur in ordinary AI projects: the firm capability you want to reuse, and the client-specific context you should not casually carry elsewhere.

Across projects
Firm methodology, reusable specialist roles, working standards and approved general knowledge. These are things you maintain once and make available where they belong.
Within the engagement
Client documents, interviews, facts, decisions, sessions and working context belong with the project room. Room access, content scopes and database permission checks govern their use.
What it buys you
The next client project can start from stronger shared methods. Review proposed reusable lessons for client details and check their intended readers before making them shared knowledge.

Continuity

Come back tomorrow without rebuilding yesterday.

Client work changes. New evidence arrives, a workshop changes the priority, a partner reframes the question, a recommendation needs another pass. The engagement keeps its material where the work happens: the documents and knowledge you added, the sessions you ran and what they produced, and the scoped memory your specialists carry between sessions. The next session starts from that rather than from an empty setup.

What that does not mean: changing your firm methodology does not rewrite work already delivered, and nothing from one client’s engagement is resurfaced inside another’s. What carries forward is what you put there.

A working pass

Start with the client problem, not the prompt stack.

Describe the outcome you need in professional terms, work with the relevant perspectives, challenge what is weak, and keep shaping the work from the same engagement. AI configuration belongs in the background; consulting judgement stays in the foreground.

Open the engagement and work from the context already there
The documents, notes, prior sessions and decisions the engagement has collected are already in the room. You are not re-briefing from scratch.
Describe the consulting outcome you need
“Turn the interviews and operating data into an initial diagnosis for partner review.” Professional terms, not prompt engineering — the AI configuration stays in the background.
Bring in the relevant specialist perspectives
A lead, the domain experts the question actually needs, a critic and a validator — configured once as durable roles, not re-described each time.
Challenge assumptions and validate weak claims
The critic questions thin logic and convenient conclusions. The validator separates what the evidence supports from what it does not, and names what is still unresolved.
Curate the material into work you can review and stand behind
The result lands in an editable report. Restructure it, rewrite it, cut what you disagree with — then generate the client-facing deliverable from the version you approved.
Return later and continue from the same engagement
Come back to the engagement rather than rebuilding it: the material, the sessions and the specialists are where you left them.

Quality

Challenge the work before it needs senior judgement.

Launchpad helps surface weak logic, unsupported claims and unresolved assumptions earlier. That does not replace the consultant.

Weak logic surfaces earlier
A dedicated critic role questions thin reasoning and unexamined assumptions while the work is still cheap to change — not after a partner has read it.
Claims get sorted by evidence
A validator role separates supported claims from unsupported ones and names the gaps, so you can see what the recommendation is actually resting on.
The accountable human still decides
What is material, defensible, commercially realistic, appropriate for this client and ready to deliver is a judgement Launchpad does not make. Nothing reaches a client without you.

The unit of value

The work should end somewhere better than a chat thread.

You do not need proof that AI can produce text. These are the consulting artifacts that survive the conversation — shaped, challenged, edited and approved by you.

Strategic diagnosis
What goes in
Discovery material, interviews and internal documents already in the engagement.
What Launchpad analyses, challenges and validates
Specialists structure the analysis; the critic challenges the findings; the validator separates what the evidence supports from what it does not.
What the client receives
A prioritised diagnosis with defensible findings, ready for partner review.
90-day roadmap
What goes in
Current-state findings and the client’s stated ambition.
What Launchpad analyses, challenges and validates
Workstreams, dependencies and feasibility are worked through and challenged before anything is sequenced.
What the client receives
A sequenced roadmap in client-facing form, with priorities you chose.
Decision memo
What goes in
The decision context, the options on the table and the evidence behind them.
What Launchpad analyses, challenges and validates
Options are stress-tested; assumptions and risks are made explicit before a recommendation is written.
What the client receives
A memo that states the recommendation, the reasoning and what it depends on.

View example deliverables →

Boundaries

Methodology can travel. Client facts shouldn’t.

Each engagement lives in its own workspace, and that separation is enforced by row-level security in the database itself — not by a filter the application might forget. What a specialist can read and remember is scoped the same way. Permissions, storage, data handling and your GDPR rights are set out in full on the security page.

Review security and data handling →

Fit

When is Launchpad worth changing how you work?

It can be entirely rational to keep your current model. Here is the honest read in both directions.

Launchpad becomes more compelling when…

Several people work across concurrent client engagements.
Your methodology is meaningfully reusable between very different clients.
Senior review matters, and it is a real constraint on how much you can take on.
Client confidentiality is non-negotiable.
You want your strongest working practices to depend less on individual setup and memory.

Keeping your current model is reasonable when…

One person performs most of the delivery.
The work is highly transactional and rarely revisited.
There is little reusable methodology to carry between clients.
The main requirement is autonomous back-office automation rather than reviewed professional client work.

Three ways in

Explore Launchpad the way you want to.

See it
Explore a pre-loaded environment
Walk through a Launchpad engagement and watch a real consulting workflow unfold through recorded interactions.
Try the interactive demo
Free recorded demo · No live AI calls
Use it
Go straight to the live product
Open Launchpad Live and use it on your own work, with your own engagement and your own material.
Go to Launchpad Live
Launchpad Live from $29/month incl. VAT
Work through it with us
Bring a workflow and talk it through
Bring an engagement, an adoption question or a security concern, and walk through it with a founder.
Walk through your use case with us
Optional founder help — no sales conversation required to start.

See it on your own engagement

Walk the read-only demo, or bring a live engagement and we’ll set the room up with you.

Explore the demo Walk through your use case with us

How Launchpad works

Each coworker has a role, instructions, knowledge, tools and a model.

Rooms keep each project’s people, context and knowledge together.

A session puts you and your coworkers around one goal, with its own working memory.

Sessions can run in different ways: you lead, a coworker leads, the team talks it through, or a set process runs.

Memory has a scope. Rooms keep project context together.

Good ideas move up into your playbook, approved by you.

Start in minutes.

The full system, for evaluators

1. System overview

Create a coworker

Assemble a team

Run a session

Save a canvas

2. Client context

3. AI specialists

4. Delivery teams

5. Sessions

6. Working material, Report Canvas, Design Canvas

7. Validation and approval

8. Memory and reusable knowledge

9. Tools and integrations

10. Security architecture

11. Technical FAQ

Which AI models does Launchpad use?

Can different specialists use different models?

How is context selected for a session?

Is client data mixed between workspaces?

What becomes long-term memory?

Can users approve or reject memory?

Can outputs be edited manually?

How are PDFs and designed outputs produced?

Can clients view an output without entering the workspace?

What integrations are currently supported?

What is stored by Launchpad?

How are AI and tool costs metered?

Can a consultancy create several client workspaces?

Can methodology be reused between clients?

Which capabilities are live, and which are planned?

The work is already spread across more places than the deliverable shows.

Keep the method reusable. Keep the client context with the client.

Across projects

Within the engagement

What it buys you

Come back tomorrow without rebuilding yesterday.

Start with the client problem, not the prompt stack.

Open the engagement and work from the context already there

Describe the consulting outcome you need

Bring in the relevant specialist perspectives

Challenge assumptions and validate weak claims

Curate the material into work you can review and stand behind

Return later and continue from the same engagement

Challenge the work before it needs senior judgement.

Weak logic surfaces earlier

Claims get sorted by evidence

The accountable human still decides

The work should end somewhere better than a chat thread.

Strategic diagnosis

90-day roadmap

Decision memo

Methodology can travel. Client facts shouldn’t.

When is Launchpad worth changing how you work?

Launchpad becomes more compelling when…

Keeping your current model is reasonable when…

Explore Launchpad the way you want to.

Explore a pre-loaded environment

Go straight to the live product

Bring a workflow and talk it through

See it on your own engagement