Product · CogniChem Assistant

Describe the problem. Approve the plan.

The Assistant turns a chemistry question into a ready-to-run job or workflow, priced for your plan. It proposes; you decide. Nothing runs until you click Approve.

Describe your problem Or browse workflows

Describe the problem
In plain language, with your files attached or a structure drawn if you have them: a target, a compound list, a question about a series.
Review the plan and its cost
The Assistant picks a ready-made workflow or a single tool, or chains the steps itself when no template fits. It fills in the inputs, checks them, and shows a card with the API's estimate for your plan.
Approve, and follow the run
Your click starts it. The Assistant can then read the run's status and results back to you in the same conversation.

Examples

Ask the way you would ask a colleague.

Look up compounds, open a binding site in 3D, draw a molecule, attach a library, build a workflow, or plan a synthesis. Answers show the structures they talk about and cite their sources; anything that costs compute ends in a plan card you approve or dismiss.

[example conversations]Fig. 01

Show me imatinib, nilotinib, and dasatinib side by side. How do they differ?

Looked up compounds

Nilotinib keeps imatinib's phenylaminopyrimidine core and changes the amide tail; dasatinib is built on a different scaffold. By RDKit's count, nilotinib (529.5 g/mol, cLogP 6.36) is outside the rule of five; the others pass. Open any structure for its full property card.

ImatinibPubChemMW 493.6 · Ro5 ✓

NilotinibPubChemMW 529.5 · Ro5 ✗

DasatinibPubChemMW 488.0 · Ro5 ✓

Nilotinib · PubChemComputed by RDKit, not measured

Formula: C28H22F3N7O
Molecular weight: 529.5 g/mol
cLogP: 6.36
TPSA: 97.6 Å²
H-bond donors / acceptors: 2 / 6
Rotatable bonds: 6
QED: 0.27
Lipinski rule of five: Fails: MW, cLogP
Veber: Pass
PAINS / Brenk alerts: None

Where does imatinib bind in ABL1? Show me the pocket.

Searched PDB
Set up a 3D view

In PDB 2HYY (2.4 Å), imatinib sits in the ATP pocket between the kinase domain's two lobes. It makes polar contacts with Ile 360, Met 318, Asp 381, His 361, Thr 315, and Glu 286, among them the hinge (Met 318) and the gatekeeper (Thr 315). I set the view to the ligand in ball-and-stick with the residues around it labelled.

PDB 2HYYRCSB PDB (CC0)Ball-and-stick · STI and the residues around itCrystal structure, Cowan-Jacob et al. (2007)

Cowan-Jacob et al. (2007), Acta Crystallogr D Biol Crystallogr, PDB 2HYY · 2.4 Å

Your drawingSketcherMW 480.6 · Ro5 ✓

I drew imatinib with a morpholine in place of the methylpiperazine. How do its properties compare?

Looked up compounds
Prepared a job plan

With the morpholine, cLogP is 4.68 (up from 4.59) and TPSA 92.3 Å² (up from 86.3). Both pass the rule of five, with no PAINS or Brenk alerts. RDKit calculates these; they aren't measured. For predicted solubility and hERG risk, ADMET Predictor scores both in one job on CPU, about $0.042 a typical run.

Computed by RDKit
Property	Imatinib	Your drawing
Molecular weight	493.6	480.6
cLogP	4.59	4.68
TPSA (Å²)	86.3	92.3
Rule of five	Pass	Pass
Alerts (PAINS, Brenk)	0	0

Swanson et al. (2024), Bioinformatics

Proposed job · waiting for you

ADMET Predictor

Steps: 1
Runs on: CPU
Estimate: Priced for your plan

abl-inhibitors.csv
2HYY.pdb

abl-inhibitors.csv · 5 molecules

abl-inhibitors.csv, opened as a compound grid
name	MW	Ro5	Alerts
Imatinib	493.6	✓	0
Nilotinib	529.5	✗	0
Dasatinib	488.0	✓	0
Bosutinib	530.5	✗	1
Ponatinib	532.6	✓	1

Here are 5 ABL inhibitors and the 2HYY structure. Dock them into the imatinib pocket.

Listed workflow templates
Prepared a workflow plan

“Screen a compound library against a target” fits. It converts your SMILES to 3D, finds the binding pocket with the Binding-Site Detector, and docks all 5 compounds with AutoDock Vina on CPUs, about $0.13 a typical run. Your two files are already filled in.

Trott & Olson (2009), Journal of Computational Chemistry
Krivák & Hoksza (2018), Journal of Cheminformatics

Proposed workflow · waiting for you

Screen a compound library against a target

SMILES → 3D embed → dock

Steps: 3
Runs on: CPU
Estimate: Priced for your plan

Dock my library against this target, but only the compounds with low predicted hERG risk.

Read workflow steps
Validated workflow
Prepared a workflow plan

No ready-made workflow filters before docking, so I chained one. ADMET Predictor keeps the compounds whose predicted hERG risk is below 0.3; they are embedded in 3D and docked with AutoDock Vina into the pocket the Binding-Site Detector finds. Every connection checks out, and you can open it in the builder to change any step.

Swanson et al. (2024), Bioinformatics
Trott & Olson (2009), Journal of Computational Chemistry

Proposed workflow · built for this request

Dock the compounds that pass an hERG filter

ADMET filter → 3D embed → dock

Steps: 4
Runs on: CPU
Estimate: Priced for your plan

How could I make imatinib? Start from the last step.

Searched tools
Prepared a job plan

The amide is the natural last disconnection: an aniline (C16H15N5) and an acid chloride (C13H17ClN2O) couple to give imatinib. To work further back, Retrosynthesis proposes ranked disconnections down to purchasable building blocks, about $0.13 a typical run on CPU. Its routes are proposals to check, not a guaranteed synthesis plan.

Amide couplinganiline + acid chloride → imatinib

Genheden et al. (2020), Journal of Cheminformatics

Proposed job · waiting for you

Retrosynthesis

Steps: 1
Runs on: CPU
Estimate: Priced for your plan

Illustrations of exchanges. Structures come from PubChem and PDB 2HYY, drawn and described by RDKit; prices, papers, and workflows are the catalog's. In the app, the plan card shows the estimate the API computed for your plan, and approving re-checks it.

What it can do

Read, look up, estimate, propose.

These are the Assistant's tools, grouped by what they are for. Everything outside this list, including starting a run, is closed to it.

Find the right workflow or tool
Searches the CogniChem product graph, reads job schemas and workflow ports, and checks a workflow before proposing it.
kg_product_searchkg_product_getkg_product_neighborhoodkg_product_how_to_runlist_job_typesget_job_schemalist_workflow_templatesget_workflow_node_portsvalidate_workflow
Look up compounds and targets
Live lookups in PubChem, ChEMBL, Open Targets, UniProt, and the RCSB PDB. Every result carries a link to its source record, and structures open in 3D set up the way you asked: a binding site, a chain by B-factor, or a superposition.
resolve_compoundslookup_chembllookup_targetslookup_uniprotlookup_pdblookup_propertiesshow_structure_view
Read the method papers
Searches the reference graph of the papers behind each method, and Europe PMC live for anything newer, so answers cite papers by DOI.
kg_reference_searchkg_reference_getkg_reference_neighborhoodlookup_literature
Price it before it runs
Estimates jobs and workflows at your plan's rates, checks your wallet, and quotes its own next turn.
estimate_jobestimate_workflowget_wallet_balanceestimate_llm_turnget_session_spend
Answer quick calculations
Converts and standardizes structures, checks drug-likeness rules, compares two structures, looks up fluid properties, and predicts with your MPNN, QSAR, reaction and thermo property models, right in the reply. These count against your plan's monthly allowance, not your wallet.
compute_convertcompute_molecule_standardizecompute_druglikeness_filtercompute_molecule_rmsdcompute_coolproplist_inference_modelspredict_mpnnpredict_qsarpredict_reaction_mpnnpredict_thermo_hybridpredict_thermo_mixture
Propose runs for you to approve
Turns the plan into a job or workflow card with its estimate. Only your Approve click starts it.
propose_job_runpropose_workflow_run
Follow the results
Checks the status of runs started from the conversation, summarizes finished results, and reads the files they produce.
get_job_statusget_result_digestget_workflow_runlist_session_artifactsget_artifact_record

Safety model

You stay in control of every run and every dollar.

The rules below are enforced by the API, not by the Assistant's instructions.

It cannot start a paid run itself

The Assistant's tools can search, look up, estimate, propose, and run quick calculations that count against your plan's monthly allowance, never your wallet. Submitting jobs or workflows, cancelling, resuming, approving, and deleting are not available to it at all; the only path to a run is your Approve click in the app.

What you approve is what runs

A proposal freezes the exact job or workflow, its inputs, and its estimate. To change anything, the Assistant makes a new proposal, or you open the workflow in the builder and launch it yourself.

Re-priced when you approve

Approving re-checks the inputs and the estimate at your current plan. If the price went up since the card was shown, nothing runs until you approve the new amount; if it went down, it runs at the lower price.

Plans stay current

A plan card stays open for 30 minutes, so an old plan can never be approved by accident later. Need it after that? Ask again and the Assistant makes a fresh card, priced at today's rates.

Every conversation has a spend cap

Assistant tokens in one conversation stop at $1.00 by default. Only your Continue click raises the cap, by $1.00 at a time. Approving a run costs no tokens; compute is billed like any other run.

Your files stay files

Attached structure files (PDB, SDF, SMILES), compound tables, and images are stored in your library and passed to jobs and calculations by reference. Their contents are never pasted into the conversation, and uploads are never added to any shared knowledge graph.

Pricing

Token rates by plan.

Low and High reasoning each have their own rates. Higher plans pay less per token.

Low reasoning: USD per million tokens
Plan	Input	Cached input	Output
Basic	$0.70	$0.07	$4.20
Starter	$0.50	$0.05	$3.00
Pro	$0.40	$0.04	$2.40
Enterprise	$0.30	$0.03	$1.80

High reasoning: USD per million tokens
Plan	Input	Cached input	Output
Basic	$7.00	$0.70	$35.00
Starter	$5.00	$0.50	$25.00
Pro	$4.00	$0.40	$20.00
Enterprise	$3.00	$0.30	$15.00

Compare plans

FAQ

Questions about the Assistant

Can I use the Assistant without it running anything?

Yes. Ask questions, compare methods, or have it price a plan. A run only starts when you click Approve on a card.

What if no ready-made workflow fits?

The Assistant builds one. It chains catalog tools by their declared inputs and outputs, checks every connection, and prices the result. Workflow cards have an Open in builder button, so you can change the plan yourself before you launch it.

What does it cost?

Assistant turns are billed per token at your plan's rate (below), within the $1.00 conversation cap. Jobs and workflows you approve are billed per second of compute, exactly as if you had launched them yourself.

Can I use my own AI client instead?

Yes. Point Claude Code, Cursor, or any MCP client at the hosted CogniChem MCP server (https://mcp.cognichem.com/mcp) with your API key to get the same jobs, workflows, and lookups. You pay your own model costs; we bill only the compute.

Where do its answers come from?

From the CogniChem product graph (what each tool does and how to run it), a graph of the method papers behind the tools, and live lookups in public databases. Lookup results link back to their source records.