Can AI replace Harvey?

01What it costs

Checked Aug 18, 2026 · source: harvey.ai.

02Could AI build it for you?

The core job: Indexes a folder of your own contracts and PDFs locally, then answers questions about them with quotes and page citations so you can check every claim yourself.

What a working version needs:

• An LLM API key, or a local model via Ollama if you would rather nothing leaves the machine
• Your own documents: no licensed case law, no statute databases, no primary sources
• Python 3.11 and a willingness to read the cited passage rather than trust the summary

The retrieval half is a weekend, the reliance half is not. The moat is licensed primary law plus an enterprise security posture that took years to clear, and a name a partner can put in a risk memo.

03What you'd give up

A law firm is not paying for text generation, it is paying for defensibility. The output has to be traceable to a licensed source, the deployment has to pass a security review that takes months, the workflows have to have been tested against how associates actually do diligence, and there has to be a vendor contract with indemnities when something goes wrong. Individual lawyers also cannot use a homemade tool on client matters without answering awkward questions about where the privileged data went. A local RAG box over your own files solves none of that and does not need to; it solves reading your own documents faster, which is a different and much smaller job.

05The build prompt

Paste this into an AI coding tool (such as Claude, ChatGPT, Lovable or Replit) to build your own version. Read the verdict first: this one is hard to get right.

Build a local document Q&A tool for my own contracts and PDFs. Python 3.11, single project, no web framework, no accounts, no telemetry.

Stack, no alternatives:
- CLI with Typer
- pypdf for text extraction, page numbers preserved
- SQLite with the sqlite-vec extension for vector storage
- OpenAI API for embeddings and answers, key from .env via python-dotenv, plus an --ollama flag that swaps to a local model at http://localhost:11434

Commands:
- ingest PATH: walk a folder, extract text per page, chunk to roughly 800 tokens with 100 overlap, store chunk text plus doc name plus page number, embed and index. Skip files already ingested unless --force.
- ask "QUESTION": retrieve top 12 chunks, then answer with an LLM that is instructed to answer only from the provided chunks and to say "not in these documents" when the answer is absent. Every claim must carry an inline citation like [contract.pdf p.4].
- sources "QUESTION": print the retrieved chunks verbatim with file and page, no LLM, so I can read the raw text.
- docs: list ingested files, page counts, chunk counts.

In scope: local-only storage in ./index.db, deterministic chunking, a --model flag, plain text output.
Out of scope: web UI, multi-user, cloud sync, any bundled case law or statute data, any attempt to cite external legal sources.

Print a one-line disclaimer after every answer: this is a reading aid over my own files, not legal advice, verify each citation.
Include a README with setup, .env.example, and a short section explaining that answers are only as good as the documents I ingested.