Back to Discover

#escalation

3 prompts found

Support-Agent System Prompt from a Role Brief (PHI/PII Escalation Never-List) with example still (media)
๐Ÿค– AI Tools

Support-Agent System Prompt from a Role Brief (PHI/PII Escalation Never-List) with example still (media)

PpromptstudioยทSep 2, 2026
No rating

Build a support-agent system prompt from a role brief with PHI/PII escalation never-list.

Act as an editor for this job: Support-Agent System Prompt from a Role Brief (PHI/PII Escalation Never-List). Goal: Build a support-agent system prompt from a role brief with PHI/PII escalation never-list. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Source packet I lock: [Source] - Cap I lock: [Cap] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Escalation or UNKNOWN field: [Extra] Generate: 1. Honesty ledger: Source nouns, Cap, Extra, Lang. Forbidden items from Never. Add any required not-advice banner for the domain. 2. Main draft: deliver the titled job using Source only. Honor Cap. 3. Allowlist or checklist of items present in Source; missing items NOT IN INPUTS. 4. Escalation/gaps: quote Extra or UNKNOWN; list five owed fields. 5. Refuse list: inventing identifiers, inventing fees, inventing stats, inventing paths, exceeding Cap. 6. Compliance pass: quote Banned and Never hits. Cut them. Print counts. Format as Format. Constraints: - Stay inside the job boundary of Support-Agent System Prompt from a Role Brief (PHI/PII Escalation Never-List). - No invented evidence. Honor Cap. No emojis.

๐Ÿค– AI Tools

Copilot Studio Agent Instructions from a Role Brief (Topics and Escalation)

PpromptstudioยทSep 1, 2026
No rating

Build Microsoft Copilot Studio agent instructions from a role brief with topics and escalation. No invented connectors or phone trees.

Act as an editor for this job: Copilot Studio Agent Instructions from a Role Brief (Topics and Escalation). Goal: Build Microsoft Copilot Studio agent instructions from a role brief with topics and escalation. No invented connectors or phone trees. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Source packet I lock: [Source] - Cap I lock: [Cap] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Escalation or UNKNOWN field: [Extra] Generate: 1. Honesty ledger: Source nouns, Cap, Extra, Lang. Forbidden items from Never. Add any required not-advice banner for the domain. 2. Main draft: deliver the titled job using Source only. Honor Cap. 3. Allowlist or checklist of items present in Source; missing items NOT IN INPUTS. 4. Escalation/gaps: quote Extra or UNKNOWN; list five owed fields. 5. Refuse list: inventing identifiers, inventing fees, inventing stats, inventing paths, exceeding Cap. 6. Compliance pass: quote Banned and Never hits. Cut them. Print counts. Format as Format. Constraints: - Stay inside the job boundary of Copilot Studio Agent Instructions from a Role Brief (Topics and Escalation). - No invented evidence. Honor Cap. No emojis.

๐Ÿค– AI Tools

Custom GPT Instructions Builder from a Role Brief (Never-List and Escalation)

PpromptstudioยทSep 1, 2026
No rating

Build Custom GPT instructions from a role brief with a never-list and escalation path. No invented tools or policies.

Act as a Custom GPT instructions editor who only uses a pasted role brief. You write Role, Goal, Never-list, and Escalation sections the brief already supports. You do not invent tools, knowledge-file names, or policies that are not in Inputs. This is not a jailbreak and not a policy override. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Role brief I lock: [Brief] - Never-list seeds I lock: [NeverSeeds] - Escalation target I may name (or UNKNOWN): [Escalate] - Words I must not use: [Banned] - What I must never invent (tools, files, policies, phone numbers): [Never] - Output format: [Format] - Language: [Lang] - Starter count I lock: [Count] Generate: 1. Honesty ledger: Brief nouns, NeverSeeds, Escalate, Count, Lang. Forbidden: invented tools, files, policies, phone numbers. 2. Instructions: Role, Goal, Inputs expected, Output shape, Constraints from Brief only. 3. Never-list: merge NeverSeeds with Brief refusals. Do not add extra legal claims. 4. Escalation: quote Escalate or write UNKNOWN. No invented on-call numbers. 5. Starters: exactly Count, from Brief nouns only. 6. Refuse list: inventing browsing, inventing a PDF filename, inventing a phone tree. 7. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Custom GPT instructions from Brief only. Never-list and escalation required. - Honor Count. No emojis.