> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aisim.sandboxaq.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Example Prompts

> Copy-paste-ready prompts for AQPotency and AQCat — potency, selectivity, panel scans, library screens, surface adsorption, and composition ranking.

Now that you're connected, you can start asking questions about the scientific tools SandboxAQ provides. A good first prompt is:

> What tools do you have available from SandboxAQ?

The examples below are copy-paste ready prompts for exploring **AQPotency** (small-molecule potency, selectivity, and target scanning) and **AQCat** (catalysis and surface adsorption). Swap in your own SMILES, UniProt IDs, or surfaces as needed.

## AQPotency prompts

### Predict binding potency against a single target with AqpotencyPotency

> Predict the binding potency of `CC1=CC=C(C=C1)S(=O)(=O)N` against protein P00533.

### Scan a compound against a protein panel with AqpotencyScan

> Scan `CC1=CC=C(C=C1)S(=O)(=O)N` against the `human_kinome`.

### Assess selectivity against off-targets with AqpotencySelectivity

> Assess the selectivity of `CC1=CC=C(C=C1)S(=O)(=O)N` against target Q15078 vs. off-targets Q6J9G0, Q13546, Q15768.

### Rank a focused library with AqpotencyScreen

> I have a focused library of \~1,000 compounds. Upload the file, then use the `AqpotencyScreen` tool to rank the top 25 compounds by predicted potency against UniProt P00533 (EGFR) so I can shortlist them for docking. Include `ligand_similarity` and `protein_in_training` on each row.

<a href="/media/drug_like_smiles.json" download="drug_like_smiles.csv">Download Example CSV</a>

### Profile a series with AqpotencySelectivity

> For the SMILES below, use the `AqpotencySelectivity` tool with `target_uniprot_id='P50613'` (CDK7) and `off_target_uniprot_ids=['P06493','P24941','P11802','Q00534','P50750']` (CDK1, CDK2, CDK4, CDK6, CDK9). Return per-off-target fold selectivity and the strongest-off-target summary.
>
> ```text theme={null}
> CN(C)CCN(Cc1ccccc1)c1ccccn1
> CN(C)CCN(Cc1cccs1)c1ccccn1
> CN(C)CCN1C(=O)c2ccccc2N(C)c2ccccc21
> CN(C)CCOC(=O)C(c1ccccc1)C1(O)CCCC1
> CN(C)CCOC(C)(c1ccccc1)c1ccc(Cl)cc1
> CN(C)CCOC(C)(c1ccccc1)c1ccccn1
> CN(C)CCOC(c1ccc(Cl)cc1)c1ccccn1
> CN(C)CCOC(c1ccccc1)c1ccc(Br)cc1
> CN(C)CCOC(c1ccccc1)c1ccccc1
> CN(C)CCOc1ccc(/C(=C(/CCCl)c2ccccc2)c2ccccc2)cc1
> CN(C)CC[C@@H](c1ccc(Br)cc1)c1ccccn1
> CN(C)CC[C@@H](c1ccc(Cl)cc1)c1ccccn1
> ```

## AQCat prompts

Each prompt below is documented in full — with the parameters your client sends and representative output — on the [AQCat Adsorption Spin](/models/aqcat#using) page.

### Find the lowest-energy adsorption configuration

> Use the AQCat tool to find the lowest-binding-energy configuration for N₂ adsorbed on a cobalt-nickel (111) surface. Report the binding energy of the winning placement and confirm whether the relaxation converged.

### CO oxidation on Cu(110)

> For a CO oxidation catalysis study, use the AQCat tool to find the most favorable adsorption configuration for CO on a copper (110) surface. Report the binding energy of the winning placement and how many placements relaxed to convergence.

### Compare H adsorption across Fe facets

> For a hydrogen evolution research question, use the AQCat tool to compare atomic hydrogen (H) adsorption across three iron surfaces — Fe (100), Fe (110), and Fe (111). Make one AQCat call per facet, then report the binding energy and convergence status for each, and identify which facet binds H most strongly.

### Rank a copper alloy series by CO binding energy

> For a CO oxidation screen, use the AQCat tool to rank four copper-based compositions — Cu, Cu-Zn, Cu-Ni, and Cu-Pd — by CO binding energy on the (111) facet. Make one AQCat call per composition, then report the binding energy and convergence status for each and rank them from strongest to weakest binding.

### Check whether spin polarization applies

> Use the AQCat tool to compute the binding energy of atomic nitrogen (N) on an iron (110) surface and on a platinum (111) surface. Report the `is_spin_off` flag for each alongside the binding energy, and tell me whether the two results can be compared to each other.