Skip to Content
IntegrationsAI providers

AI providers

Bidderops’s AI features are powered by a pluggable provider layer. You bring your own model access, configure it per feature, and Bidderops routes each request to the provider you chose.

Supported providers

ProviderModelsNotes
OpenAIGPT-4o, GPT-4o MiniDirect API.
AnthropicClaude Opus 4, Claude Sonnet 4, Claude Haiku 4Direct API; native web search.
GoogleGemini 1.5 Pro, Gemini 1.5 FlashDirect API.
OpenRouterAny model in the OpenRouter catalogA gateway to many providers; the live catalog is fetched and cached.
LocalAny model on an OpenAI-compatible endpointRuns on your hardware. See Local LLM.

A model is identified by a provider:model string — for example openai:gpt-4o, anthropic:claude-sonnet-4-6, or local:mistral.

The AI features

Each of these features can be pointed at a different model, with its own editable instructions, in Settings → AI:

FeaturePurpose
Go/No-Go AdvisorRecommends whether to pursue an opportunity.
RFP AnalyzerExtracts scope, criteria, milestones, and dates from RFP text.
Discovery BoostScores how well sourced tenders fit your bid profile.
Portfolio InsightsSummarizes win/loss patterns across your portfolio.
Bid Intelligence AgentResearches a single opportunity into a dossier.
Bid Intelligence Deep DiveExpands one section of a dossier in depth.
Pipeline ReportProduces an executive briefing on the active pipeline.
Experience ImportExtracts references and CVs from documents.

Where keys live

API keys and your local endpoint settings are stored per organization, server-side. They are never shipped to the browser — the AI calls are made from the server, so your credentials stay on the server. You can configure keys for several providers at once and switch between them per feature.

Web-search grounding

Two features — Bid Intelligence and its Deep Dive — are far more useful when the model can search the live web. Grounding support depends on the provider:

ProviderGroundingHow
AnthropicYes (native)web_search tool
OpenRouterYesthe :online model suffix
OpenAIBest-effortResponses API web_search_preview
GoogleBest-effortGoogle Search grounding
LocalNofalls back to ungrounded generation

When a provider cannot ground, the report is still produced — it is simply marked grounded: false. This matters most when running a local model.

Customizing instructions

Every feature ships with sensible default instructions describing the model’s role. You can override them per organization in Settings → AI. A fixed output contract (the required JSON shape) is always appended in code so responses stay machine-readable — that part is not editable.

Last updated on