ContextWorks · Security
Every answer runs as the person asking.
Permissions enforced in the query itself, not filtered from the output after the model has seen the data.
Security · September 30, 2026
Same Tool, Same Record, Two Users, Two Payloads
How ContextWorks shapes agent context with domains and enforces security with Salesforce permissions. Two users, one record, two correct payloads.
Read post →
Security · September 12, 2026
Filtering the Answer Doesn't Make It Safe
Trimming an agent's results after the query leaves the model holding data the user can't see. Learn why enforcement belongs in the query itself.
Read post →
Agents · September 8, 2026
Your Agent Can Reach Every Field. That's the Problem.
Giving an agent every field makes it confidently wrong and quietly unsafe. See why curated, permission-correct context beats wider access.
Read post →
Nothing published on this topic yet.
