Intelligent IntegrationsIntelligent Integrations

Projects

Gates, harnesses, and delivered systems.

Twelve public Python and JavaScript gate repositories, with five selected projects featured here, alongside aggregate outcomes from forward-deployed enterprise AI leadership. Public tests use synthetic fixtures; private employer work stays private.

Open-source evaluation & governance harnesses

Nothing ships until it passes a gate — and the gate itself must be earned.

Five selected projects from 12 public Python and JavaScript gate repositories. These are tested, CI-checked harnesses using synthetic fixtures, not employer or client production deployments; each repository documents its limits.

[00]

jbisaccia-9/verify-gate

Document-verification gate with explicit human approval before release.

Gate
Source facts, disclosure, file fidelity, eligibility, and byte-bound human approval must all clear.
Evidence
21 tests; 9/9 valid packets passed, while 6/6 counterexamples were refused.
Limits
Synthetic fixtures and non-production harness; not evidence of an employer deployment.
VerificationHuman approvalRelease gate

[01]

jbisaccia-9/mcp-gate

MCP file-access server with an enforced roots boundary below the prompt layer.

Gate
Canonicalize and resolve paths before the authorized-root check.
Evidence
11 tests; boundary mode blocked all 4 escape attacks that leaked through prompt-only control.
Limits
Synthetic fixture/reference harness, not an employer deployment.
MCPTool securityAuthorization

[02]

jbisaccia-9/target-gate

Healthcare provider-targeting pipeline where delivery is blocked until data-quality gates pass.

Gate
Checksum, freshness, dedupe, field coverage, market coverage, and brief grounding must pass.
Evidence
CI enforces ≥80% field coverage and rejects a deliberately hallucinated provider brief.
Limits
CI and demos use fixture snapshots; adapters are production-shaped, not a deployment claim.
PipelinesData qualityAzure

[03]

jbisaccia-9/rag-gate

Retrieval quality gate for RAG systems — the index only serves once retrieval is good enough.

Gate
Serves only at recall@3 ≥ 0.90.
Evidence
Recall@3 1.00 and MRR 0.958 on the current 12-query labeled set; an earlier 0.83 baseline was correctly blocked.
Limits
Small, hand-labeled evaluation set; live NVIDIA embedding path requires API access.
RAGRetrieval evalCI gate

[04]

jbisaccia-9/roi-gate

Conservative adoption and value model that refuses unsupported ROI claims.

Gate
Realization discount, all-seat costs, license cost, excluded roles, and zero benefit for inactive users.
Evidence
7 tests; the conservative model passed and all 5 vendor-deck assumptions were refused.
Limits
Synthetic adoption data and methodology, not an employer deployment.
ROIAdoptionEvaluation

Professional engagements

Delivered inside employer and client environments.

~/projects/hipaa-clinical-ai-function▍

01 · Behavior Frontiers · Jul 2026 – Present

Enterprise AI function for a national behavioral health network

Outcome

Sustained 99.97% run success across 18,454 production runs, with 11 of 12 workflows at or above a 95% success target. The first independent accuracy measurement verified 2,197 records across eight checks with zero errors; all five production failures were integration or authentication issues resolved within one to two days, with no logic defects.

What it enabled

Built and deployed 12 production AI workflows across regulated clinical, HR, and operational processes, with governance, independent validation, and value measurement built into delivery.

Context

A national behavioral health network needed secure enterprise AI delivery and organization-wide adoption in a regulated setting.

Architecture

Secure Azure-based delivery with status- and error-code-only telemetry, independent output validation against source systems the workflows do not control, and no client data leaving the protected environment.

Security

Regulated delivery grounded in access boundaries, privacy review, and fail-safe behavior that refuses to publish incomplete results.

Governance

Weekly run and accuracy scorecards support sustainable billable-hour growth, denial prevention, and service capacity without disclosing private workflows or client data.

Technologies

Enterprise AIAgentic workflowsGovernanceAdoption
~/projects/solar-rag-chatbot▍

02 · Capital Energy · Sep 2025 – Jul 2026

Customer-facing RAG chatbot with agentic logic

Outcome

Reduced response times by 40% and increased self-service adoption for inbound queries.

What it enabled

Designed and deployed a customer-facing RAG chatbot with agentic logic that answers inbound solar queries directly and hands off when human help is needed.

Context

Inbound solar inquiries arrived faster than the team could answer them, slowing response times and pushing routine questions onto sales staff.

Architecture

Retrieval over the company's product and process documentation, agentic routing for multi-step questions, and integration with existing customer channels.

Security

Scoped credentials for integrated systems and constrained retrieval sources to approved company content.

Governance

Prompt iteration guided by output review and response-quality evaluation before broader rollout.

Technologies

RAGPrompt engineeringAgentic logicAPI integration
~/projects/lead-reactivation-agent▍

03 · Capital Energy · Sep 2025 – Jul 2026

Outbound lead reactivation agent

Outcome

Automated prospect engagement at scale and accelerated sales pipeline growth.

What it enabled

Built an outbound reactivation agent using Voiceflow, Twilio, and ElevenLabs to automate prospect engagement and route interested leads back to sales.

Context

A large backlog of dormant prospects sat untouched because manual outreach did not scale with the sales team's capacity.

Architecture

Conversation flows in Voiceflow, telephony and messaging via Twilio, synthesized voice via ElevenLabs, with outcomes written back to the CRM.

Security

Scoped API credentials per integrated service and controlled contact lists for outreach.

Governance

Human handoff for qualified conversations and review of agent transcripts to tune behavior.

Technologies

VoiceflowTwilioElevenLabsCRM administration
~/projects/crm-migration-automation▍

04 · Capital Energy · Sep 2025 – Jul 2026

CRM migration and operational automation program

Outcome

Reduced manual operational work by 40% and setup time by 30%.

What it enabled

Led the CRM migration to Core 365 as technical project manager — data migration, workflow redesign, and system integration — and designed Make and Zapier automation pipelines across operations.

Context

Fragmented systems and manual handoffs made operational work slow to run and slow to set up for new campaigns and teams.

Architecture

Migrated CRM data model and redesigned workflows, with Make and Zapier pipelines connecting CRM, communications, and internal tooling.

Security

Controlled data migration with scoped access during cutover and per-connection credential management.

Governance

Staged migration plan with stakeholder sign-off, workflow documentation, and post-cutover support.

Technologies

Core 365MakeZapierCRM administrationAPI integration
~/projects/frontier-model-training▍

05 · Handshake AI · Outlier AI · Mercor · Nov 2024 – Present

Model training, evaluation, and RLHF contract work

Outcome

Directly informs how I design evaluation and hallucination-mitigation practices for enterprise deployments.

What it enabled

Ongoing contract work performing expert data annotation and dataset curation for LLM training pipelines, evaluating outputs against reward metrics, and contributing to RLHF and preference-data workflows.

Context

Frontier AI platforms need expert human judgment to curate training data and evaluate model behavior on technical and conversational tasks.

Architecture

Platform-provided annotation and evaluation environments with rubric-based scoring and preference comparison tasks.

Security

Work performed under each platform's confidentiality and data-handling requirements; project specifics are not disclosed.

Governance

Rubric-driven scoring focused on response quality, alignment, consistency, and hallucination mitigation.

Technologies

LLM evaluationRLHFPreference dataPrompt engineering

Representative capabilities

Where I lead and build.

Capability areas rather than delivered case studies — shaped by applied AI engineering and enterprise delivery.

[00]

RAG and retrieval infrastructure

Ingestion, chunking, and retrieval over private corpora with citation-first synthesis and access-aware sourcing.

[01]

Agentic workflow development

Tool-using agents scoped to defined business processes, with human handoff at the points that need judgment.

[02]

LLM evaluation & hallucination mitigation

Rubric and reward-metric evaluation of model outputs, applied before rollout and revisited as prompts and models change.

[03]

Governed, compliant AI architecture

Secure enterprise AI patterns for healthcare and other regulated industries, including HIPAA-aware infrastructure design.

[04]

Automation & systems integration

Make, Zapier, and API-level integration across CRM, communications, and internal tooling.

[05]

Adoption, training & change management

Stakeholder engagement and training enablement so distributed teams actually use what gets built.

Explore the complete public portfolio on GitHub

Clone, run the tests, and read the limits each repository documents. Client and employer work stays private.

github.com/jbisaccia-9
Discuss a similar engagement