Research library
Chemistry and synthesis
View the four-date completion graphs and reconstruction notes.
Promise and evidence
AI could discover better reaction routes and make experimental optimization faster and less wasteful. Coscientist demonstrates tool-assisted experimental planning and execution, including reaction optimization. The research motivates testing complete experimental workflows rather than only text answers about chemistry.
Apply the shared measurement protocol. Targets are proposed.
Dated baseline coverage
All linked measurable-outcome files below contain an evidence baseline reviewed November 7, 2026, with source dates, findings, limitations and follow-up measurements. These distinguish measured results from proxies and unknown values; they do not assert that proposed milestones are achieved. See the baseline coverage notes.
Progress estimates
Judgment-based estimates as of November 7, 2026, using the same 0–100% scale and five-part rubric as mathematics. 0% anchors the period before ChatGPT's public release in 2022; 100% requires AI to manage this field's continuing advancement without human participation. Confidence is low. These are evidence-based judgments, not empirical completion measurements, forecasts or percentages of jobs replaced.
| Measurable outcome | Estimated progress | Execution / breadth / agenda / validation / improvement (each out of 20) |
|---|---|---|
| Experimental efficiency | 35% | 10 / 5 / 5 / 10 / 5 |
| Process burden | 10% | 5 / 5 / 0 / 0 / 0 |
| Route execution | 30% | 10 / 5 / 5 / 5 / 5 |
| Substantial novelty | 15% | 5 / 5 / 0 / 5 / 0 |
| Transfer and scale | 30% | 10 / 5 / 5 / 5 / 5 |
| Yield and selectivity | 35% | 10 / 5 / 5 / 10 / 5 |
Each linked outcome explains its score, cites its dated evidence baseline and identifies the next measurement. Zero indicates no qualifying post-anchor progress established by the reviewed evidence for that outcome, not proof of no relevant capability. Do not average these overlapping indicators into a field-wide percentage or interpret their differences as a precise ranking of fields. All outcomes reaching 100% would still require a separate field-wide demonstration of sustained autonomous advancement.
Measurable features
| Feature | Measurement and acceptance rule |
|---|---|
| Route execution | Target compounds obtained at required purity / all assigned synthesis targets, confirmed experimentally. |
| Yield and selectivity | Isolated yield and measured selectivity under matched conditions; distinguish isolated product from inferred instrument signal. |
| Experimental efficiency | Number of experiments, elapsed days, human hours, and total dollars to meet a frozen yield and purity specification. |
| Process burden | Kilograms of waste per kilogram of product, solvent use, energy per batch, and total production cost. |
| Substantial novelty | New transformations or materially different routes accepted after literature and patent review; distinguish routine parameter tuning. |
| Transfer and scale | Success on unseen substrate families and retention of yield, purity, and reproducibility at increased scale. |
Evidence requirements
Archive experimental protocols, analytical data, unsuccessful trials, instrument logs, and human interventions. Require independent execution of claimed new routes. Evaluate chemical identity and mass balance rather than accepting plausible descriptions. Compare with both expert chemists and established optimization methods under equal experimental budgets.
Proposed milestones
Meet prespecified purity and yield targets on at least eight of ten held-out synthesis tasks, with at least three reproduced independently.
Reduce experiments or total cost to specification by at least 25% across three reaction families without relaxing quality requirements.
Establish one substantially new useful transformation or route, independently reviewed and reproduced in a second laboratory.
Retain the claimed advantage over three batches at ten times the initial scale. Faster chemical discovery is a scientific benefit; repeated acceleration of the experimental discovery process is the more relevant feedback signal.