— 01
Call-document ingestion
Parses the full call documentation — scoring rubric, regulatory framework, cost categories, eligibility criteria. Produces a structured requirements tree.
GrantAI
A composed pipeline for grant-application drafting. Parse the call, score eligibility, draft sections against the published rubric, simulate evaluator scoring before submission. First POC: our own FENG Ścieżka SMART application.
Pillar 04In buildPOC: FENG Ścieżka SMARTEU + UK funders
What it does
Capability surface
— 02
Eligibility scoring
Scores organisational eligibility against the call's published criteria. Tells you whether to invest in drafting before committing six months of preparation.
— 03
Section-by-section drafting
One specialised agent per required section — impact, commercialisation, work-package plan, budget. Each agent with its own rubric awareness and domain context.
— 04
Coherence QA across sections
Reads the full draft and flags contradictions between sections — the most common failure mode in multi-author grant work. Budget mismatches, timeline inconsistencies, impact claims unsupported by the work plan.
— 05
Evaluator-scoring simulation
Simulates evaluator review against the published rubric. Scores each section 1–5 with reasoning. Flags below-threshold sections before you commit to submission.
— 06
Multi-funder rubric support
Point at a different call — FENG, Horizon Europe, Innovate UK, ARIA, Interreg — and the pipeline produces the same outputs against that funder's specific rubric.
Who it’s for
Buyer profile
R&D-active SMEs pursuing grants
Firms with genuine research to fund, currently paying grant consultancies 8–15% success fees.
You qualify for FENG or Horizon Europe but the preparation cost is prohibitive. GrantAI lets you run the application in-house at a fraction of consultancy cost, with full ownership of the source material for future applications.
Grant consultancies scaling wins
Consultancies running grant applications as a service.
Same pattern as TenderAI for consultancies — scale wins with licences instead of headcount, reuse expertise across adjacent calls without re-writing, and produce inspectable reasoning for every scoring decision.
How it’s built
Agent pipeline
Not a single prompt or a chatbot. A composed pipeline of specialised agents, each with a defined role, a documented toolset, and a declared failure mode.
agent/ingest-grant-callParses call documentation, scoring rubric, cost categories. Produces a structured requirements tree the other agents work against.
agent/score-eligibilityScores organisational eligibility against the call's criteria before drafting effort is committed.
agent/draft-impactSpecialised agent for the impact narrative — reads EU research priorities, aligns the firm's claim to funder strategy.
agent/draft-workplanWork-package and milestone drafting with matched budget logic. Ensures budget-to-WP alignment.
agent/coherence-checkReads the full draft. Flags contradictions between sections — the silent killer of multi-author grant work.
agent/simulate-evaluatorScoring gate. Simulates evaluator review against the published rubric. Scores 1–5 per section with reasoning attached.
Status
In active build · POC complete
Status
In active build. POC complete. The POC was our own FENG Ścieżka SMART application, drafted end-to-end through the platform.
Target launch
Pilot deployments Q3 2026.
Funders targeted first
FENG (PL), Horizon Europe, Innovate UK, ARIA.
Also in scope
R&D tax-credit rubrics — UK RDEC/SME, Polish B+R — shared with TaxAI.
Compliance
GDPR compliant. Firm-level data isolation. Your past-application corpus stays yours.
Engage early
enterprise@blackflake.com — describe the funder and call you are targeting.
How we engage
Built for your firm. Developed with you.
Every deployment is a bespoke engagement. We don't sell seats or generic SaaS. We build agents against your workflows, your matter taxonomy, your regulatory context — then we operate the system with you under a monthly retainer. Your data, configurations, and outputs are yours and portable. The Blackflake engine is developed by us and runs under your retainer.
— 01
Discovery
Scoped call to map your workflow, constraints, and success metrics. No charge. You leave with an architecture note and engagement estimate.
— 02
Pilot build
Fixed-price deployment on one narrow workflow. Real output on real work in weeks. Go / no-go before the full build.
— 03
Full build
Agent suite, workflows, sources of truth, QA gates, operator surface. Deployed in your tenant. Auditable.
— 04
Retainer
Monthly retainer: new regulations ingested, agents tuned on live work, new workflows added. We develop the engine; your data, configurations, and outputs stay yours — always portable.