Market research

Market Research helps you understand what's available on the market before you write your RFP or evaluate bids. The agent searches the web, reads product and supplier pages, and compiles structured findings backed by real, verifiable sources.

It runs in two ways:

• Inside a procurement — the agent prices the items extracted from the procurement's technical specification: candidate suppliers with the public contracts they have already won, one price row per source per item, and a written report. See Research inside a procurement.
• Standalone — describe what you want to research in a brief, optionally upload reference documents, and get categorised findings and a report. See Starting a standalone research run.

When to use it

• Before writing an RFP — validate that your technical specifications match what's actually available on the market
• Generating specifications — you know what you need but don't have a formal spec yet; the agent researches the market and drafts one
• Supplier discovery and pricing — find potential vendors for the exact items you are buying, see what they have won before, and collect sourced prices for an estimate
• Regulatory check — identify relevant standards, certifications, and compliance requirements for your procurement domain

Research inside a procurement

When a procurement has an approved item catalogue, market research works from that list instead of a free-text brief. Open RFP → Items, approve the items you want researched, and click Start market research.

Confirm the scope

Before anything is charged, a confirmation page shows how many approved items and how many distinct products the run will price. Identical items across lots count once. Billing follows what the run actually does; a failed run costs nothing, and the cost is not knowable up front because it depends on how many pages the agent has to open and read.

What the run does

1. Supplier discovery — the agent searches for suppliers of the approved items and matches each one to comparable awarded contracts from published tender data.
2. Pricing — in two passes, it collects price observations for every distinct product: first from the suppliers it found, then from the open market.
3. Report — it writes up the supplier landscape, price observations, and recommendations.

While the run is in flight, the Items, Suppliers, Prices, and Report tabs all carry the same progress banner, and the results appear on each tab as they come in. Only one research run per procurement can be active at a time.

Suppliers tab

One row per candidate supplier: name, description, the source page it was found on, the comparable contracts it has already won (value, tender title, conclusion date), a confidence level, and a review status.

Select suppliers and use Approve selected or Reject selected. Approved suppliers are the ones offered to the pricing pass first. A run that finished without naming any supplier says so; approving more items and running it again usually widens the search.

Prices tab

One row per price observation per item, grouped by CPV code. Each row shows the supplier (linked to the source page), the product and manufacturer, the price with its currency and unit, the price basis (list price, contract price, past award, or on request), whether the product meets the specification (with a note when it falls short), and the date the price was observed. Below the product you also see the offer terms the source states, such as warranty, delivery, and availability.

Under each price, the VAT basis shows VAT included, VAT excluded, or VAT exempt. It is set only when the source states the VAT treatment in its own words; otherwise the row shows VAT not stated. Check it before you compare prices.

Each item also shows what happened to it in the pricing pass:

An item edited after the run started is marked Edited since research, because the quotes describe what the item was when it was dispatched.

Export to Excel writes the same rows to a workbook, one row per quote per item. A quote found for a group of identical items repeats against each of them, so the price column must not be summed. Besides the price columns, the workbook includes VAT basis, Offer terms, and Gaps and unknowns columns.

Report tab

The written report from the end of the run: executive summary, supplier landscape, price observations, and recommendations for the specification and the tender structure.

Starting a standalone research run

Understanding findings

Each finding includes:

• Title — the claim or discovery
• Description — details and context
• Type — one of: Product, Specification, Supplier, Regulation, Risk, Recommendation
• Confidence — HIGH, MEDIUM, or LOW
• Sources — clickable URLs with extracted evidence from the original pages

Confidence levels

Each finding shows a confidence rationale explaining why the agent assigned that level — for example, "3 manufacturer sources, 2024-2025 data" or "single reseller listing, no manufacturer confirmation."

Navigating findings

Findings are organized into views:

• Overview — summary statistics: products found, insights recorded, documents created
• Products — an expandable table of product and supplier discoveries
• Insights — other finding types (regulations, risks, recommendations) organized by category

Click any finding to expand it and see all sources with extracted evidence. Source URLs are clickable — verify claims directly on the original websites.

Working with research documents

The agent produces one or more editable documents:

• Market Research Report — executive summary, market overview, key findings, supplier information, pricing data, regulations, and recommendations
• Technical Specification (if the research warrants it) — technical requirements and qualification criteria backed by market data

Each document opens in a rich text editor with the same toolbar used for RFP composition. Changes are auto-saved.

Guided mode

In Guided mode, the agent pauses after its initial research pass. You'll see the findings so far and a text input where you can provide feedback:

• "Focus more on pricing and availability"
• "Investigate supplier X in more detail"
• "Ignore products below capacity Y"

The agent incorporates your feedback and continues. This gives you control over the research direction without having to specify everything upfront.

Reference documents

Uploading reference documents (specs, standards, RFPs) helps the agent in two ways:

1. Context — it understands your specific requirements and constraints
2. Validation — it can compare what it finds on the market against what you already have, flagging gaps or opportunities

Uploaded documents are parsed and indexed automatically. They appear in the Overview section so you can see what context the agent used.

Statuses

A research run moves through a small set of statuses, visible in the run header and on the research list:

The Run again and Download Excel actions appear once the run reaches Completed.

Credit cost

Market research runs consume credits based on AI processing. Web searches and page fetching are low-cost; the main expense is the AI reasoning about what it finds. Typical observed costs are 0.5–1.0 credits per research run, with simple briefs at the lower end and broad multi-iteration runs at the upper end. The exact charge appears in the run summary after completion (for example, Completed in 21m 25s · 13 products / services · 2 insights · 0.55 credits).

See Credits and pricing for how credits are billed across the platform.

Reference document formats

Reference documents go through the same upload pipeline as RFP and bid documents — see Working with documents for the full table. In short: PDF, Word (.doc, .docx), Excel (.xls, .xlsx), PowerPoint (.ppt, .pptx), Markdown, and .edoc archives are accepted. Files must finish parsing before the agent can use them.

Limitations and things to know

• Concurrent runs. Market Research allows up to 3 active runs (Pending, Running, or Paused) at the same time, counted across your whole organization — not per user. The New Research button is disabled only once you already have 3 active runs, with a tooltip explaining the limit. Wait for one to finish, or delete it, before starting another. Funding Research enforces its own separate limit, so you can run Market Research and Funding Research in parallel.
• Run time. A research run usually takes between a few minutes and roughly half an hour. There's no fixed estimate shown up front; the activity feed is the most reliable progress indicator.
• Deleting a run. Each Market Research run has a Delete research action that removes it permanently. Use this if you need to free up the concurrency slot or clear out experimental briefs.
• Reference documents must be parsed. Uploaded references run through the same parser as RFP and bid documents. Don't start the run until each reference shows Completed status.

From research to procurement

Market Research feeds naturally into the rest of the platform:

1. Research the market to understand what's available
2. Use the findings to write a well-informed RFP (manually or via Compose RFP)
3. Extract the items from the finished specification and price them inside the procurement
4. Upload vendor bids and run analysis against your market-backed requirements