3rd-gen agentic SaaS · reference tenant: Ashford Partners

Win bids faster. Stop starting from scratch.

OpenBid turns a consultancy’s 14 years of accumulated knowledge into a living, governed, agentic capability — so every proposal team can find what the firm already knows, identify the right people, and produce a credible first draft in hours, not days.

Grounded · cited · access-controlled · human-gated. Trust is the binding constraint — and we engineered for it. The model never receives a document the user isn’t entitled to see.

Hours
to a first draft, not days
60–70%
of bid time today is searching
8/8
governance & trap eval cases pass
3
interchangeable agent runners
Northwind Bank
Payments modernisation · £3M pursuit
Drafting
Proposal section · “Why Ashford”

We have delivered comparable financial-services outcomes and can reuse accredited assets, shortening time-to-value… [d0001 · proposal]

reuse rate
0.67
confidence
high
🛡️Governance: clearedwall: Sterling Union excluded

Competitor (Sterling Union) material was filtered out of retrieval before the model saw it. Every cited asset is one this bid team is entitled to reuse.

runner claude-agent-sdk · 3 entitled sources · grounded
The knowledge problem

A firm’s edge is what its people know — but that knowledge is trapped.

14 years of deliverables sit in SharePoint and local drives. Expertise data goes stale in a CRM. There is no shared research repository. When a bid arrives, proposal teams spend 60–70% of their time searching — and credible-but-lost opportunities cost millions a year. The core thing AI must solve is not “write proposals” — it is making the firm’s collective memory instantly and safely usable at the moment of a bid.

Platform

Six agents. One governed knowledge layer.

Grounded, cited, access-controlled by construction — and measured every release.

🧭

Bid Orchestrator + 5 specialists

A supervisor agent decomposes a bid into a plan, then delegates to Knowledge Retrieval, Expertise Routing, Proposal Drafting, Market/Freshness and Governance agents — parallel reads, sequential writes.

📚

Hybrid retrieval, grounded & cited

Dense + sparse fusion over 14 years of proposals, deliverables and methodologies. Every passage returns with its citation, a confidence score, and a stale flag.

🧑‍🤝‍🧑

Expertise graph — derived, not declared

Who-knows-what is mined from the work itself, not a stale CRM. Ask 'who's done this, in this sector, at this seniority' and get ranked people with evidence.

🛡️

Governance in the data, not the prompt

Access control is a pre-retrieval query filter — the model never receives a chunk the user can't see. Confidentiality tiers, Chinese walls, PII scrub, full audit.

Freshness that flags itself

Time-decay by document type — market intel decays in months, methodology in years. Stale content surfaces with a badge and a ranking penalty, never silently.

🤖

Triple-runner, one tool surface

OpenAI Codex SDK, Claude Agent SDK, or a dedicated RAG agent with hard guardrails — all sharing one RAG-over-MCP tool surface. Autonomy where safe, structure where it matters.

The agent-architecture story

Three generations of AI agents. We ship the 3rd.

Plus a deterministic guardrail agent for the safety-boundary cases.

1st gen

Pure RAG

Chunk + embed + retrieve. Useful for Q&A; can't route people, draft, or govern access.

2nd gen

Framework agents (LangGraph-era)

Hard-coded DAGs. Brittle. Hard to evolve as the knowledge base and policies change.

3rd gen

Autonomous file-aware agents

Claude-Code-style — read the corpus, plan, call tools — paired with a deterministic guardrail agent for the cases where structure must beat autonomy.

What we ship
How it works

From a knowledge archive to a grounded first draft.

01

Ingest the knowledge

Connect SharePoint / drives. Documents are parsed, typed, chunked, embedded and stored with governance + freshness metadata in pgvector.

02

Build the expertise graph

Authorship and staffing signals derive a self-maintaining graph of who-knows-what at concept level — no admin burden, no stale CRM.

03

Orchestrate the agents

A bid brief fans out to retrieval, expertise and market scans in parallel; drafting, governance and review run as one auditable chain.

04

Ship a grounded first draft

A cited draft with a reuse rate and confidence — human-gated at plan, shortlist and review. Below confidence or across a wall, it escalates, never fabricates.

Trust, proven

Autonomy where safe. Structural guardrails where it matters.

Our test corpus has three planted traps. The platform catches all three — verified, re-runnable, in every release scorecard.

Freshness

Stale intelligence

A 2019 market outlook is surfaced with a stale badge — never reused as if it were 2026 truth.

🔒Access control

Confidential leak

A restricted M&A document is invisible to everyone — including the Managing Partner — except the entitled deal team.

⚖️Conflict wall

Conflict of interest

A competitor's proposal can never cross the Chinese wall to the rival client's bid team, even when explicitly requested.

Use cases

One platform, every practice.

Ashford Partners is the reference tenant — strategy, operations and technology advisory across four sectors.

Financial Services

Ashford sector

Open banking, core-banking migration, payments modernisation, regulatory remediation — repurpose prior bids and surface the right regulatory specialists.

Energy

Ashford sector

Net-zero transition, smart metering, grid data platforms — with confidential M&A work walled off to the deal team by need-to-know.

Healthcare

Ashford sector

EHR implementation, patient-flow optimisation, workforce planning — reuse accredited methodologies and clinical case studies.

Public Sector

Ashford sector

Digital identity, procurement transformation, shared-services operating models — credible first drafts grounded in real prior delivery.

ROI

“How will I know this is working?”

Month 1: a baseline and adoption. Month 6: search time and draft time falling, reuse climbing. Year 2: a win-rate and bid-cost number — measured against a control cohort, with caveats you can audit. Framed as capacity and win-rate, not “AI”: every proposal hour saved is a billable hour returned; a point of win-rate on a £3M bid is ≈ £30k.

Pricing

Open-source community. Commercial for the firm.

AGPL-3.0 community license. Commercial license for firms with revenue ≥ £250k or air-gapped deployments.

Community

Free
AGPL-3.0
  • Self-host the full stack
  • All 3 runners + RAG-over-MCP
  • Synthetic Ashford reference dataset
  • Eval harness + governance trap suite
  • Community support
Clone on GitHub
Most popular

Practice

£1,499
/ tenant / month
  • Hosted multi-tenant SaaS
  • Unlimited corpus per workspace
  • Tenant-isolated pgvector + expertise graph
  • Azure OpenAI / Anthropic / OpenAI
  • ACL pre-filter + Chinese walls + audit
  • Email + Slack support, 1-day SLA
Start trial

Enterprise

Custom
annual contract
  • Single-tenant or on-prem (VPC / k8s)
  • Live SharePoint / CRM connectors
  • Bring-your-own LLM keys
  • Custom governance + conflict policies
  • Per-release eval scorecards
  • SLA up to 99.9%
Contact sales

See the firm’s memory, safely.

Open the live demo — pick a persona, ask a question, and watch the platform ground its answer in entitled material, flag what’s stale, and refuse to cross a confidentiality wall.