> Source: https://ashareapi.com/en/agent-quant/ · Markdown version for LLMs / AI agents Agent quant # What is Agent quant In traditional quant, a human writes the strategy. In Agent quant, the agent does the research. The bar moves from “can write Python” to “can ask” — but so does the bottleneck: it is no longer whether the strategy is right, but whether the agent made it up. In one sentence **Agent quant = letting the agent run the whole loop — hypothesise → fetch → backtest → validate** — while the human only asks and adjudicates. What it needs is not more data, but **checkable data** — because when an agent is wrong you cannot tell what it computed from what it invented. ## How it differs from traditional quant This is not the same job done better — it is a **different executor**. Change the executor and the bar, the bottleneck and the platform’s role all change with it: | | | | Traditional quant (JoinQuant / RiceQuant / Uqer / MyQuant) | Agent quant | | Who researches | A **human** writes the strategy | The **agent** does the research | | Who the data serves | Strategy code written by a human | The agent directly (MCP) | | Barrier to entry | Can write Python | Can ask | | Main bottleneck | Is the strategy right? | **Did the agent make it up?** | | Platform’s role | Data + backtest engine + strategy community | **Trustworthy data layer** | | Degree of automation | Human sets rules, machine executes | Agent proposes and validates on its own Who researches A **human** writes the strategy The **agent** does the research Who the data serves Strategy code written by a human The agent directly (MCP) Barrier to entry Can write Python Can ask Main bottleneck Is the strategy right? **Did the agent make it up?** Platform’s role Data + backtest engine + strategy community **Trustworthy data layer** Degree of automation Human sets rules, machine executes Agent proposes and validates on its own ⚠️ The key distinction: “AI” on traditional platforms means an LLM helps you **write strategy code** (the human stays in the loop) ⇒ they build a **Copilot**. We build the base for an **Autopilot** — the agent completes fetch → hypothesise → validate → iterate on its own. ## The sharpest edge: checkable The biggest risk in Agent quant is not too little data — it is “the AI made it up and you did not notice”: Traditional quant Traditional quant goes wrong: a human wrote the code, so you **can debug it** Agent quant Agent quant goes wrong: **you cannot tell computed from invented** ⇒ So what Agent quant really needs is not more data but **checkable data**. These design choices are not marketing — they are what makes an agent’s conclusion **reproducible**: | | | Our design | What it means for the agent | | K-lines are **fixed to forward-adjusted**, no `adjust` parameter, no gap on ex-dividend days | Returns the agent computes are **reproducible** — run it again later, same answer | | Consistent units (yuan / share / lot spelled out) | The agent cannot get the order of magnitude wrong | | Empty result ≠ failure | The agent will not read “no data” as “the service is down” | | Fixed envelope `{ ok, endpoint, tier, elapsed_ms, source, data }` | The agent can tell for itself whether the call succeeded K-lines are **fixed to forward-adjusted**, no `adjust` parameter, no gap on ex-dividend days Returns the agent computes are **reproducible** — run it again later, same answer Consistent units (yuan / share / lot spelled out) The agent cannot get the order of magnitude wrong Empty result ≠ failure The agent will not read “no data” as “the service is down” Fixed envelope `{ ok, endpoint, tier, elapsed_ms, source, data }` The agent can tell for itself whether the call succeeded ## What the loop looks like Agent quant is not “ask once, get a stock list” — it is a chain you can audit: 1 Connect the data Expose data as tools the agent can call (MCP or REST) — not as web pages for it to read 2 Propose a hypothesis The agent proposes: “after a volume breakout above the 20-day high, what is the 5-day hit rate?” 3 Fetch The agent calls tools for real data — structured, documented, reproducible 4 Backtest Adjudicate on statistical thresholds: enough sample, confidence-interval lower bound > 0, out-of-sample direction consistent 5 ⚠️ Catch the fabrication The conclusion does not match the data — this step is the real difficulty of Agent quant 6 How to catch it Recompute from the raw data. **Fixed conventions** mean recomputation must match — fabrication shows up immediately ## Our boundaries, up front This page is about a category, not a promise. Three things we do not do: We do not promise returns We will not tell you which stock will rise. You get the data and the validation method; the call is yours. We do not touch automated trading We provide data and validation only — no order placement, no account access. We do not compete on “how accurate the AI’s stock picks are” That is a returns promise aimed at retail. Ours is a capability promise for developers: **how do you check what the AI said**. ## Ready to build This page defines the category; these show how to do it: [AI quant: data and validation (full guide)](/en/docs/ai-quant) Four data paths compared · REST and MCP routes · the four traps that fool a backtest [A-share quant research with MCP](/en/docs/guides/ai-quant-mcp) Fetch → backtest → adjudicate, with four adjudication rules [MCP setup](/en/mcp) One URL into Claude Code / Cursor / Codex and more ## FAQ Is Agent quant the same as “AI stock picking”? No. AI stock picking usually means a model hands you a list of tickers (a returns promise aimed at retail). Agent quant means the agent runs the whole research loop — fetching, computing and validating (a capability promise for developers). We do not promise picks; we guarantee the data is checkable and conclusions reproducible. Can I do Agent quant without programming? You can start. Agent quant moves the bar from “can write Python” to “can ask” — you state the hypothesis and the agent fetches and computes. But **adjudication** is still yours: is the sample big enough, does it hold out of sample. Why does “checkable” matter so much? In traditional quant a human wrote the code, so a bug can be debugged. In Agent quant the conclusion is generated, and when it is wrong you cannot tell computed from invented. Fixed conventions (forward adjustment, consistent units, a fixed envelope) are therefore not details — they are the precondition for using an agent for quant at all. Do you provide backtesting? Yes. Single-stock / portfolio backtests and batch backtests across many symbols × many strategies, with commission / stamp duty / slippage / price limits. The strategy and factor libraries are callable too. See the MCP setup page. Start with one real data point Free tools (quote / K-line / hot list / market overview / breadth) need no key — connect and let the agent run its first loop. [MCP setup](/en/mcp)[Pricing](/en/pricing)