Review preparation
A review preparation agent assembles the client summary before an annual review from the emails, notes and documents the adviser can already open, so the meeting starts prepared rather than cold.
Industries / Financial advisers
AI agents for advice firms
AI agents can take hours out of review preparation, meeting follow-up and client correspondence. In a regulated advice business they have to be built so the adviser's judgement, the audit trail and client confidentiality stay intact. We design and build them inside your own Microsoft 365 tenant.
FiveForward designs and builds AI agents for UK financial advisers and wealth managers, working in Copilot Studio inside the firm's own Microsoft 365 tenant across annual review preparation, meeting follow-up and client correspondence, so preparation gets faster while advice, suitability and sign-off stay with the adviser.
Advice firms sit on exactly the work AI agents are built for: long client histories, meeting notes, review packs, correspondence and the constant search for the right document. The same firms carry FCA obligations, Consumer Duty expectations and some of the most sensitive personal data any business holds. Both things are true, so agents need to be designed with care rather than caution alone.
The right agents prepare rather than advise. A review preparation agent assembles the client summary before the meeting, a follow-up agent turns the conversation into file notes and first-draft letters and a correspondence agent drafts from wording the firm has already approved. Each one is built in Copilot Studio inside your own Microsoft 365 tenant and works only on material the firm already holds. The recommendation and the reasoning behind it never move away from the adviser.
Delivery should also recognise that an advice firm is several jobs, not one. Advisers, paraplanners and administrators each lean on different preparation, so agents are scoped role by role with agreed review points on every one. Firms that want to build for themselves can: we train builder teams through hands-on agent workshops, and when end user Copilot adoption training is needed it is arranged through our training partner.
Our work follows the FiveForward Framework, a five-stage method covering Discover, Design, Enable, Automate and Embed.
Comparable builds
These examples come from related workflow patterns, and the sector label on each card is the real one, so you can see exactly where the parallel holds. We have not yet published a case study from this sector itself.
Worked example · Accountancy and audit
A document automation build from an accountancy and audit practice: standard letters generated from structured data with wording the responsible person can trust. The same agent pattern applies to client agreements and routine review correspondence in an advice firm.
Read the related case studyWorked example · Property and professional services
A worked example set in a professional services firm running client work across offices, with its system surfaced inside Outlook. The client-record and correspondence pattern carries across to advisers, paraplanners and administrators.
Read the related case studyAdvice workflows
Agents help an advice firm most in the preparation and follow-up around client work, never in the recommendation itself. These are the workflows agents and Copilot usually take weight out of first.
A review preparation agent assembles the client summary before an annual review from the emails, notes and documents the adviser can already open, so the meeting starts prepared rather than cold.
An agent turns review meetings into file notes, actions and first-draft follow-up letters, drafted while the conversation is fresh and checked by the adviser before anything is sent.
Drafting support assembles the adviser's notes and approved paragraphs into a structured first draft. The recommendation, reasoning and final wording stay with the adviser and compliance.
A correspondence agent drafts routine letters and emails from approved wording, keeping tone consistent across the firm without retyping the same paragraphs.
A research summary agent summarises fund, provider and market documents as preparation, with the source document still checked before anything is repeated to a client.
An internal agent answers questions on the advice process, templates and compliance guidance from approved SharePoint sources, without depending on one person's memory.
Jobs for agents and automation
Risks to manage
Where agents fit
Agents belong in an advice firm once the job is bounded, the source is approved and the output is treated as preparation for a qualified adviser, never as advice.
The practical territory is review preparation, meeting follow-up, guided client intake, internal process guidance and compliance lookup. Anything that recommends, and anything a client reads unchecked, stays with a person, with agreed review points on every agent.
Each agent is built in Copilot Studio inside the firm's own Microsoft 365 tenant, inherits the permissions the firm already runs and reads only approved sources. Most scoped builds take two to six weeks from Design sign-off.
A review preparation agent that assembles the client summary, held documents and open actions before the adviser starts
A meeting follow-up agent that drafts file notes, actions and follow-up letters for the adviser to check
A client intake agent that gathers initial information and prepares a structured handover
An internal process agent for the firm's advice process, templates and how-to questions
A compliance lookup agent that points staff to current firm rules and escalation routes
A plain-English guide to when agents help, where they should stop and how regulated firms should govern them.
Design and build for focused agents around review preparation, follow-up and client intake.
How a firm goes from a free consultation to working agents, stage by stage.
Related routes
Scoped agent builds for advice firms, typically £5,000 to £15,000 depending on the number of agents, the systems they connect to and the state of the source data.
The £1,500 fixed first stage. With Design it produces the workflow map, prioritised agent use cases and costed roadmap for the firm's agents.
Hands-on sessions for the firm's own builder team. An agent workshop ends with a working first agent built and running in your tenant.
The automation layer around agents, moving documents and data between the systems an advice firm already runs.
Common questions
Yes, as preparation and drafting tools inside a properly governed Microsoft 365 tenant. The firm remains responsible for advice, records and data protection, so permissions, grounding sources and review points are settled at Design rather than after rollout. Nothing that recommends is ever handed to an agent.
It can assemble a first draft from the adviser's own notes and the firm's approved paragraphs. The recommendation, the reasoning and the final wording stay with the adviser and the firm's compliance process. It is drafting support, not an advice engine.
The agents we build run inside your own Microsoft 365 tenant. They inherit your existing permissions, so an agent can only read what the person using it can already open. Prompts, responses and grounding data stay inside the Microsoft 365 service boundary and are not used to train the underlying models. The remaining work is your own permissions hygiene, which is why we check it before any agent is grounded.
Indirectly. Clearer, more consistent client communications and better file notes support the outcomes the Duty asks for. An agent is not a compliance tool and it does not change the firm's obligations.
Review preparation is the usual answer: an agent that assembles the client summary, held documents and open actions before the adviser starts. Client intake and an internal process agent for the firm's advice process and templates are the other early candidates. A first declarative agent takes about 15 minutes to build in a workshop, which is a useful way to see the shape of the work.
Agents are strongest across Outlook, Teams, Word, Excel and SharePoint, which is where most of the preparation and correspondence around a back-office system already happens. Where the system has a usable connector or API, Power Automate can carry data between it and Microsoft 365, and we are honest at Design about what each system can and cannot reach.
Yes. Where the roadmap points that way, your team ships its first agents and automations from the roadmap with us alongside: £3,950 fixed, with two delivery days, two build reviews and 90 days of async support answered within 2 working days. Agent workshops start from £850 for three hours live, run as a half day or two 90-minute sessions, with a full day at £1,500, and an agent workshop ends with a working first agent built and running in your tenant.
Scoped builds are typically £5,000 to £15,000 depending on the number of agents, the systems they connect to and the state of the source data. The price is fixed at Design before work begins, and most scoped builds take two to six weeks from Design sign-off.
Start with a free 30 minute consultation, no pitch, no obligation. It is the same first step for every firm. The first paid stage is Discover at £1,500 fixed, which covers Discover and Design together and is priced for organisations up to around 50 staff, with larger firms scoped individually on the consultation with the same credit terms. Together the two stages produce a workflow map, prioritised agent use cases and a costed roadmap, and Design ends with a playback session of about an hour where you pick the route and the price is fixed. The £1,500 is credited back in full once follow-on spend passes £3,500 before VAT within 90 days of the roadmap.
Recommended starting point
Custom agents grounded in the right knowledge and built for defined jobs, in your own tenant.
Most firms start with Discover, a fixed-fee first step that maps your workflows and finds the agent opportunities before any build. Details are on the pricing page.
Other industry pages
AI agents can draft variance commentary, keep board packs consistent and take the chasing out of month-end. We design and build them in Copilot Studio inside your own Microsoft 365 tenant, tied to the reporting calendar and to review discipline.
AI agents can take real weight out of people work: policy questions, onboarding, manager guidance and repeat admin. We design and build them inside your own Microsoft 365 tenant, with the boundaries sensitive employee data demands.
AI agents earn their place in marketing when they take on the work around the writing: research synthesis, brief drafting, repurposing and content operations. The voice and the editorial judgement stay with your team.
Concierge