ScopeSmith — an AI proposal generator that runs on a $0 local model

Description and use

ScopeSmith enables freelancers to swiftly convert unstructured client messages into professional proposals, eliminating scope‑creep risks and speeding client acquisition while keeping data private.

Problem

Freelancers spend excessive time converting vague client briefs into structured proposals, often missing out‑of‑scope items and falling victim to scope creep, which leads to unpaid work and lost revenue.

Outcome

ScopeSmith enables freelancers to produce professional proposals in under a minute, eliminating scope creep, reducing unpaid work, and accelerating client acquisition, with a cost‑effective local model that keeps client data private.

Workflow

• Paste messy client brief into ScopeSmith
• Local model (Qwen2.5-1.5B-Instruct via Ollama) processes brief through four-stage pipeline: extract → scope → red flags → terms
• Generate structured proposal in markdown
• Review and send proposal to client

Evidence

ScopeSmith turns a messy client brief into a client-ready proposal in under a minute.

Source

Paste a rambling WhatsApp export, a half-formed Upwork message, a rambling email — you get back a structured proposal: scope of work, concrete deliverables, an explicit out-of-scope list, the top scope-creep risks with countermeasures, and freelancer-friendly payment terms

Source

The project is a small Python package: scopesmith/ providers.py # LLMProvider ABC + ollama / openai-compatible / mock backends prompts.py # the four stage prompts + proposal renderer pipeline.py # extract → scope → red flags → terms orchestration cli.py # python -m scopesmith entry point

Source