On-site · 1–5 days Working PoC on exit

We come in.
We build it.
You own it.

A focused on-site sprint that leaves your finance team with a deployed AI agent — built on your actual data, running before we leave.

Duration
1–5 days
Format
On-site or hybrid
Output
Deployed PoC agent
Team size
Finance teams of 3+
Reserve a spot — first cohort limited
✓ Received. We'll be in touch within one business day.
We respond within one business day.
1–5 Days on-site
1 Working PoC on exit
80+ CFO conversations
2nd Cohort — revised scope

Not a course.
A deployment.

Most AI programmes teach your team about AI. This one builds something with them. We arrive with a clear sprint scope, work directly in your environment, and leave a working agent running on your real data.

The team doesn't just watch. They build alongside us — so when we leave, they own it and can extend it themselves.

01
Scoped before we arrive

A pre-session call maps your workflows, data sources, and PoC target. Day 1 starts with a clear objective, not a discovery exercise.

02
Built on your actual data

No synthetic demos. We work in your environment — your GL, your ERP, your reporting stack. The agent is live the moment it's done.

03
Handed over and documented

Every sprint closes with full documentation, a prompt library, and a roadmap of the next agents worth building.

Three phases. Variable duration. The structure is fixed — the time allocated to each phase scales with your team's size, starting AI maturity, and the complexity of the PoC target.

Phase 01
Map
½ day – 1 day

We map your team's recurring workflows against a finance-specific AI readiness matrix. The output is a prioritised list of use cases — with a clear decision on which PoC to build, and which workflows should not use AI unsupervised.

  • Workflow-AI Matrix across your finance function
  • Data sources audit — what exists, what's accessible, what's clean
  • PoC target selected and scoped
  • Governance guardrails agreed
You leave with
Sprint brief, prioritised agent backlog, clear guardrails
Phase 02
Build
1 day – 3 days

We build the PoC agent live, in your environment, on your real data. Your team builds alongside us — not watching. We use Claude Cowork for non-technical participants and Claude Code where deeper integration is needed. The agent runs before this phase ends.

  • Finance context layer — COA, KPI definitions, reporting logic
  • Claude accounts configured for finance-specific tasks
  • Agent built and deployed on your data
  • Iteration loops until output is production-ready
You leave with
A deployed, working agent running on your actual data
Phase 03
Embed
½ day – 1 day

We hand over everything — documentation, prompt library, knowledge base — and run a structured session to make sure the team can operate, extend, and maintain the agent independently. We also set the data architecture direction for moving from Copilot mode to autonomous operation.

  • Agent fine-tuned based on team feedback
  • Full prompt library and documentation handover
  • Data architecture roadmap for autonomous operation
  • Next agents prioritised and scoped
You leave with
Docs, knowledge library, agent roadmap, architecture brief
Note

Duration scales to your team. A CFO and two analysts can complete all three phases in 2 days. A finance function of 10+ typically runs the full 5 days. We agree the timeline on the discovery call — before we arrive.

We scope the PoC together during the Map phase. Below is the full menu — pick one for the sprint, use the Embed session to sequence the rest.

Balance sheet reconciliation agentReconciles BS lines to sub-ledgers, flags variances, drafts commentary
Accrual agentIdentifies missing accruals based on historical patterns and open POs
Month-end close trackerTracks task status, chases owners, flags blockers in real time
Intercompany reconciliation agentMatches interco balances across entities, surfaces mismatches
Journal entry reviewerFlags unusual entries vs. historical patterns before sign-off
Audit trail generatorAuto-documents the reasoning behind journal entries and adjustments
Variance commentary generatorActual vs. budget narrative, board-ready, in your house style
Revenue forecasting modelDriver-based forecast that updates automatically as actuals come in
Rolling forecast updaterIngests actuals, rolls forward assumptions, outputs a refreshed forecast
Financial modelThree-statement or unit economics model connected to live data
Budget formats agentBuilds and populates budget templates from prior-year actuals and targets
Scenario modellerWhat-if on key drivers — headcount, FX, churn, price — instant output
Performance dashboardLive KPI dashboard connected to your data sources, refreshes automatically
KPI tracking agentMonitors KPIs against targets, alerts on breaches, drafts commentary
Report integration & shareAssembles reports from multiple sources and distributes to stakeholders
Board pack generatorPulls from data sources, populates templates, drafts narrative sections
Management reporting agentAuto-populates standard management packs on close, every month
ESG reporting agentCollects non-financial data, maps to frameworks, drafts disclosures
Cash flow forecasting agent13-week rolling forecast, pulls from bank feeds and AR/AP ledgers
Covenant monitoring agentTracks debt covenants against actuals, flags risks before breach
FX exposure trackerMonitors multi-currency positions, flags concentration risks
Payment terms optimisation agentAnalyses AR/AP terms against cash position, recommends adjustments
Pricing anomaly detectorFlags deals outside standard terms before they hit the books
Customer profitability agentAllocates costs to customers, ranks by margin contribution
Churn early-warning agentFinance-side signals — payment delays, contract shrinkage — surfaced early
Cost centre overspend alertMonitors actuals vs. budget by cost centre, alerts owners on breach
80+
CFO conversations
Built from a year of direct conversations with finance leaders — mapping where AI creates real value and where it creates real risk.
Big 4
Advisory backgrounds
The team trained at EY and Deloitte. We understand reporting cycles, audit requirements, and the accuracy standards a finance function can't compromise on.
2-in-1
Advisory + product
incro is a finance advisory firm. CFO Studio is our AI-native financial analysis platform. The bootcamp brings both together.
Built by the founders of
incro
Boutique financial consulting
CFO Studio
AI-powered financial analysis platform

5 days.
One working agent.
Yours to keep.

Every sprint is scoped before we arrive. One 30-minute call is enough to design the session, pick the PoC, and agree the timeline.

Book a discovery call
✓ Received. We'll be in touch within one business day.
We respond within one business day.
Or reach us directly
hello@incro.pl