Startup Ideas Bank

Ambitious software for a real pain, but it reads like a research lab dressed up as a product.

AI roast score: 68/100 (C)

The idea

You did not invent autonomous research. You wrapped a hard coordination problem in prettier words and called it a product. The killer question is whether anyone pays for persistent evidence loops instead of just using more agents.

In the founder's own words

sapientinc/PRAXIST — Autonomous research system for measurable, computer-executable research.

Praxist: meet your personal R&D team





Praxist is an autonomous research system for measurable, computer-executable
research. It coordinates parallel research peers, task-owned evaluation,
durable evidence, and generation-to-generation synthesis.

Praxist treats research as a persistent process rather than a sequence of
disconnected prompts. Use it when a project already runs and its objective is
measurable, but the best path forward is still unknown.



Install Praxist

Install the complete runtime integrations and finish first-use setup with one
command:

python3 -m pip install --index-url https://pypi.org/simple " praxist[agents,codex] " && praxist setup --interactive --install-skills codex

The local wizard covers the Fair Source License, User Agreement, privacy,
runtime profile, masked credentials, Codex skills, writable examples,
and readiness checks. It does not select a research project or launch a run.
For Claude Code, use the
host-specific one-line command .

For an agent-managed installation, open Codex:

codex --yolo

Then ask it to install and configure Praxist using the packaged OOBE runbook,
and to stop after readiness checks.

Before starting research, read the Quickstart
and Your First Task . They describe the
separate takeover step and the project contract it creates.

Choose Codex-native mode to use an existing Codex subscription without an
API key. For sustained research, Praxist generally favors
open-source model APIs with a high
observed cache-hit rate. The setup wizard also supports other API-backed
profiles.

Use Praxist Through Codex

We recommend Codex as the interface for operating Praxist. Praxist is not a
replacement for Codex: Codex remains the interactive agent that understands
your project, communicates with you, and uses development tools. Praxist adds
the persistent research loop, parallel peers, evidence protocols, scheduling,
and lifecycle control.

After installation, open Codex in the root of an already runnable research
project and invoke $praxist-takeover . The takeover skill inspects readiness,
creates or repairs the task harness, validates its evaluator and evidence
contract, and launches the run after the required gates pass. A precise brief
produces a better research plan; include the objective, metrics, constraints,
resources, exploration choices, and whether launch is authorized.

Example takeover brief
$praxist-takeover

Treat the current directory as the existing runnable research project. Verify
the baseline and its evaluation path before changing anything.

Optimize <primary metric and direction> while preserving <key constraints>.
Use <peer count> peers for up to <generation coun

The roast

This is smart-sounding software, and that is the problem. The pitch is packed with phrases like “autonomous research system,” “parallel research peers,” and “durable evidence,” but almost none of it proves a buyer will pay. You say the user is a professional or enterprise buyer, but the product still feels like a tool for people who love systems more than people who need outcomes. The core promise is also slippery. You want to be “a personal R&D team” for “measurable, computer-executable research,” which sounds powerful until you ask who owns the budget and what gets replaced. A solo founder with no funding and a product-led plan is trying to sell a complex subscription/license product to developers and professionals across the world. That is not impossible, but it is a long, cold road. The biggest weakness is that the pitch is mostly architecture, not pain. You describe setup commands, takeover flows, evaluator contracts, and model profiles in painful detail, but the customer problem is still vague. If the buyer cannot point to a repeated, expensive research workflow that breaks today, then this becomes a nice demo for technical people and a weak business for everyone else.

Red flags

Verdict

If you can prove one repeatable research workflow saves real money, this could work; if not, it stays a clever tool for insiders.

Start with your own startup idea →

More ideas roasted by AI

Browse all startup ideas →