Assemble proposals from past engagements
From a brief or a call summary, the system finds the most relevant past proposals, case descriptions and team bios, assembles a first draft in your template and flags every claim that needs checking. For firms where each proposal starts by copying an old one.
Function: Sales · Industry: Professional services
Assemble proposals from past engagements
6 steps
At a glance
- Trigger
- A partner or manager requests a proposal for a prospect.
- Typical inputs
- Prospect brief or call notes
- Past proposals and statements of work
- Approved bios, credentials and case descriptions
- Fee rate cards and proposal template
- Systems it usually connects to
- Google Drive
- SharePoint
- Salesforce
- HubSpot
- How the work splits
2 rules, 2 model, 2 person steps
How it runs, step by step
6 steps, each tagged by what does the work. Rules are fixed logic, a model reads or drafts, and a person decides.
- Rules Fixed logic in code
- Model AI reads or drafts, with a confidence score
- Person A named person decides
- 1
Understand the brief
ModelA model identifies the service, sector, scope and timeline from the notes and asks for any missing basics.
- 2
Find the relevant material
ModelPast proposals and approved case descriptions are ranked by similarity to this brief.
- 3
Assemble the draft
RulesSections are placed in your template from approved language, with bios and credentials pulled from the approved library.
- 4
Flag what needs checking
RulesClient names, dates, figures and promises taken from past work are marked for review, and confidential material is excluded by rule.
- 5
Write the judgment sections
PersonThe partner writes the approach, the pricing logic and anything that depends on the relationship.
- 6
Approve and send
PersonA partner reviews the full draft and the firm's risk process signs off where required.
Where people approve
The decisions that stay with your team, whatever the confidence score says.
- A partner approves every proposal.
- Confidential material from past clients is excluded unless cleared.
- Fees are set by a person.
KPIs to track
What to measure, before and after. Targets come from your own baseline.
- 01Hours from request to first draft
- 02Proposals sent within your target turnaround
- 03Win rate by proposal type
- 04Flagged items found in review
Questions about this workflow
Could it leak another client's information?
That is the main risk, so past material is filtered by an approved-for-reuse flag and by rules for client names. Anything that slips through is caught by the review step, which is why the flagged-items list matters.
Does it write the fee section?
It can lay out a fee table from your rate card and past scopes. The partner decides the price, because the commercial logic is the part clients negotiate.
Which steps use rules, a model and a person?
Rules: assemble the draft; flag what needs checking. Model: understand the brief; find the relevant material. Person: write the judgment sections; approve and send. Rules are fixed logic in code. A model reads or drafts and reports its confidence. A named person decides.
What do we need to start?
Typically: prospect brief or call notes; past proposals and statements of work; approved bios, credentials and case descriptions; fee rate cards and proposal template. You also need read access to Google Drive, SharePoint, Salesforce and HubSpot, or the equivalents you use. A workflow audit measures your volumes and past cases first, then gives a fixed price for the build, so you can decide with real numbers.