AI for consultancies and advisory firms.
We build AI for consultancies that sell expertise by the project: management, IT and engineering firms and advisory practices. Proposals start from your best past work, consultants find the right reference without asking around, and the admin between CRM, planning and invoicing takes less manual work.
Where the work gets stuck
Proposals rewritten every time
Every tender and proposal needs references, CVs and a method section that already exist somewhere in SharePoint or Notion. Finding and rewriting them takes time senior consultants should spend on the client's problem.
Knowledge that leaves with people
Project learnings sit in final reports and in the heads of whoever ran the engagement. When those people move on, the firm loses the context and repeats the research.
Utilisation hidden behind admin
Hours are written late, project budgets are checked at month end and invoices wait for someone to reconcile Simplicate or AFAS with the contract. Partners learn a project overran after the fact.
What we build for consultancies
Each one is scoped around your systems and rules, and each one keeps a person in charge of the decisions that matter.
Proposal and tender assistant
The assistant reads the request for proposal, finds matching references, CVs and method text from past bids and drafts a first version in your template. The bid manager edits it, and the responsible partner approves every submission.
Project knowledge search
Consultants search final reports, workshop notes and deliverables across SharePoint, Confluence or Notion, and get answers that name the project and the document. Client-confidential material stays restricted to the people cleared for it.
Account research before a pitch
An agent reads the prospect's annual report, recent news and CRM history and writes a one-page brief into the HubSpot or Salesforce deal. The consultant walks into the meeting knowing the client's situation.
Time and budget tracking
Draft time entries are suggested from calendars and the documents people worked on, and budget use is checked daily against the contract. Project leads confirm the entries and get a warning before a budget runs out.
Client tools from engagement models
Many engagements end in a spreadsheet model that the client keeps asking for. We turn the ones worth keeping into a web tool the client logs into, which the firm can offer as an ongoing service.
CRM, planning and finance integration
A won deal in HubSpot creates the project in Simplicate or AFAS with budget and team, and approved hours flow to invoicing in Exact. Client data is typed in once.
Built around the rules
What we design for from the first week. These notes are general information and are not legal advice, and your legal and compliance people keep the final word.
Client confidentiality and NDAs
Engagement letters and NDAs often restrict where client material may be stored and whether it may be used with AI tools. We map those terms to access rules and keep restricted material out of shared search.
GDPR and processing agreements
Proposals, CVs and project files contain personal data of staff and client contacts. We work under a data processing agreement, share our sub-processor list and keep data in EU regions.
Security questionnaires from enterprise clients
Large clients ask consultancies for ISO 27001 or SOC 2 aligned controls before they share data. We build with logging, access reviews and documentation that make those questionnaires easier to answer.
AI literacy under the EU AI Act
Organisations that use AI systems must take measures to support the AI literacy of the staff who use them, a duty that has applied since 2 February 2025. We hand over short guidance on what each tool does, where it fails and when to check its output.
Works with what you run
If a system has an API, a database, an export or an inbox, we can build on it. These are the systems common in this sector.
- HubSpot
- Salesforce
- AFAS Profit
- Exact Online
- Simplicate
- Microsoft 365
- Microsoft Teams
- SharePoint
- Notion
- Confluence
Where to start
Proposal assistant for one service line
A proposal assistant is a practical first use of AI for consultancies. We take one service line with a steady flow of proposals and index its past bids, references and CVs. The first release drafts reference sections and CV summaries for a live tender, which your bid team compares with its own version.
Talk it throughWhat it includes
- Index of past proposals, references and CVs
- Drafting in your Word template
- Access rules for client-confidential projects
- Review of drafts against submitted bids
Related work
A guide to start with
Further reading
Embeddings explained: a practical guide for product teams
How embeddings power semantic search, how to choose a model and a vector store, and how to measure whether your results improved.
5 min read
Human-in-the-loop AI agents: design patterns for real operations
How we keep a human in the loop when AI agents run on live systems: approval checkpoints, confidence thresholds, tool permissions, audit trails and fallbacks.
5 min read
How to build a RAG chatbot people can trust: a practical guide
What it takes to turn a promising RAG experiment into a chatbot people trust: ingestion, hybrid search, citations, permissions and evals.
6 min read
Common questions
Only if you allow it. Each document carries the access rules of its source, and confidential projects can be excluded from drafting or limited to the team that ran them. Drafts list the sources used, so the bid manager can check.
Yes. Both have APIs for projects, hours and invoices, which we use to link planning, time and finance with your CRM. We check early which fields your firm relies on, because configurations differ a lot between consultancies.
They will if the assistant only has a model's general knowledge. Ours drafts from your own winning bids and method texts, in your template and terminology, and the consultant adds the client-specific thinking.
Yes. We work white-label for consultancies and agencies, so you keep the client relationship while we build behind you. Our partners page explains how that works.
You or your client, as your contract sets out. We transfer code and documentation in full and do not reuse client-specific work elsewhere.