Loading
One moment.
Platform · agents · release 2026.4
Thirteen agents, three pillars, one intelligence layer.
NODES is the intelligence layer and system of action for enterprise decisions, starting with hiring. Thirteen agents across the same calibrated scoring substrate, trained on your own production outcomes. Agents specialize. The model underneath does not split.
The agent roster
Three pillars. One scoring substrate.
Agents are not separate models stitched together. They are specialized surfaces on top of the same calibrated weights, nodes-substrate-2026.04. A signal seen in sourcing compounds into the retention stream ninety days later. A signal seen in an HR ticket compounds into the manager intelligence stream a quarter later. Same model. Different decision.
Stage 01
Hire & Develop
The decisions that put the right person in the right seat and keep them growing.
Stage 02
Operate & Run
The decisions that keep the back office moving without losing auditability or speed.
Stage 03
Sell & Grow
Extension area. The same intelligence layer extends to revenue systems as the substrate compounds.
Pillar 2 pilot target-30% HR ticket cycle time
Inference p5074ms, data egress: zero
Anatomy of an agent
Inputs on the left. Model in the middle. Actions on the right.
Every agent is a thin orchestration layer over the same calibrated substrate. Swap the prompt, not the model. Swap the output surface, not the weights. That is why an interview score, a retention signal, an HR ticket resolution, and a deal slippage flag all agree. They read the same evidence.
Inputs · evidence
What the agent reads
ATS candidate recordreq · resume · stage▸
- source
- Workday · Greenhouse · iCIMS
- fields
- req_id, stage, resume_parsed, recruiter_notes
- cadence
- webhook · sub-second
Structured interview transcriptsigned · timestamped▸
- source
- agent · 02 · structured interviewer
- payload
- utterance stream, 6 signal flags, sig-hash
- retention
- customer-vpc · indexed by req_id
HRIS production stream18-mo rolling▸
- source
- UKG · ADP · Workday HCM · Rippling
- signal
- RPA, premium-per-month, retention event, comp band drift, ticket activity
- window
- rolling 18-mo · refresh weekly
CRM pipeline eventsper-agent cadence▸
- source
- Salesforce · Dynamics · HubSpot
- signal
- activity cadence, pipeline velocity, conversion
- grain
- per-agent · per-week
Persona query resultlearned pattern▸
- source
- agent · 03 · persona sourcing
- payload
- candidate + provisional fit + source attribution
- pattern
- learned · not keyword
Ticketing system eventswebhook · sub-minute▸
- source
- ServiceNow · Zendesk · Jira · Freshservice
- signal
- ticket category, resolution time, escalation pattern
- cadence
- webhook · sub-minute
Calendar + email metadatametadata only▸
- source
- Google Workspace · Microsoft 365
- signal
- meeting cadence, account engagement
- policy
- metadata only · no content scraping
Substrate · one model
The calibrated weights
model.id · nodes-substrate-2026.04
nodes-substrate-2026.04
fine-tuned · customer-vpc · quarterly retrain
orchestration · agent wrapperthin
prompt · signal mapper-agent
calibration · role · locationreq-level
policy · boundariescustomer-owned
Outputs · actions
What the agent writes back
Fit Score · 0-100ats native field▸
- writes to
- ATS candidate.fit_score (native field)
- calibration
- per-role · per-location · req-level
- shape
- integer 0-100 · 28-dim breakdown · rationale
Rationale · plain englishreviewer-facing▸
- writes to
- ATS candidate.rationale · reviewer view
- content
- which dims drove the score · top 3 · bottom 3
- length
- 3-5 sentences · never hedged
Decision tracesigned · reproducible▸
- writes to
- audit stream · SIEM export
- signature
- sig-hash · per-req · chain-linked
- replay
- reproducible on quarterly retrain
Signal streamweekly · webhook▸
- writes to
- manager inbox · HRIS · BI warehouse
- cadence
- weekly · delta since last emission
- payload
- retention risk, ramp drift, coaching flag
Cohort forecastmonthly rollup▸
- writes to
- Snowflake · Databricks · BigQuery
- grain
- cohort × role × location · p10/p50/p90
- calibration
- reweighted against outcomes monthly
Recommended actionmanager inbox▸
- writes to
- manager email · Slack · Teams
- content
- one action per agent · grounded in trace
- policy
- customer-owned thresholds · no auto-fire
Drafted resolutionticketing system▸
- writes to
- ticketing system · policy clause cited · approver tagged
- approval
- human approval required
- trace
- Decision Trace signed per resolution
Adverse-action floor checkaudit stream▸
- writes to
- audit stream · validator service
- verification
- floor verification · structurally enforced
- chain
- sha256-immutable Decision Trace
Agents in concert
One requisition, four agents, one human gate, one trace. (Pillar 1 example.)
Requisition rv-2412-08831, Commercial Lines Producer, Austin. The sequence agents execute and a person approves, start to finish, in the Hire & Develop pillar. Every output below is signed and writes back to the same trace chain. The same trace structure runs across the other two pillars.
trace · rv-2412-08831 · producer.commercial.austin
day 0req opened
day 2sourcing
day 6screening
day 14interview
day 34offer accepted
day 62post-hire
01
agent · 03 · Sourcing
Materialized 218 passive candidates from public professional profiles against the
top_producer_commercial_lines_austin persona, with notice and consent flows configured to counsel's requirements.218 candidates4 sourceslearned pattern
provisional fit74 +
02
agent · 01 · Screening (pipeline triage)
Deduped against the active pipeline, re-ranked by req-level calibration, routed 42 to screening and 12 to direct-sourcing outreach.
dedupe 38routed 54ats writeback
queued54
03
agent · 01 · Screening (fit score)
Scored 54 candidates across 28 dimensions. Top of funnel: M. Rojas, score 87, p-74 vs. the austin-commercial cohort. Rationale and trace written back to Workday.
28 dimstrace signedworkday native
top score87
04
agent · 02 · Interview
Conducted 12-minute async interview. 4 of 6 canonical signals present (resilience, process reset, self-audit partial, prospecting drive). Transcript signed, hash chained to screening trace.
12:04 recorded4/6 signalssig hash · 0a91f…d72e
advance87
05
human · hiring manager · approval gate
Reviewed the drafted advance and the interview evidence. Approved the interview advance, edited the comp band note, declined the parallel req transfer. Rationale logged to the trace. Nothing below ran before this sign-off.
approve · edit · declinerationale on-recordtrace co-signed
approvedd16
06
agent · 04 · Ramp
Handed off to ramp agent at day 34. Role-calibrated onboarding plan scheduled against the austin-commercial 62-day SNA median. Retention signal stream activated on week 2.
sna target · d62retention stream · onmanager briefed
milestoned62
one model · one trace · four agents · one human gate
req closed · d34 · trace · dc_8871_2026-04-14
The same primitive in the other two pillars:
Operate & Run
HR ticket trace: ticket received, context classifier (HRIS, BU, manager), policy lookup, resolution drafted, HRBP approval, Decision Trace signed. Four agents, one trace, 4-minute median cycle.
Sell & Grow
Slipping deal trace: deal stage change detected, signal stream comparison against prior slippage patterns, recovery play drafted (missing exec, talking points), CRO approval, outreach executed, Decision Trace signed. Three agents, one trace, week-three intervention before week-six slippage.
Same model. Same substrate. Same signed trace. Different decision.
Governance
Every agent inherits the same boundary.
No agent is a SaaS call. No agent loads a third-party model. The substrate runs inside your cloud account, retrained on your data, audited against your controls.
Deployment
Customer VPC, single-tenant
AWS · Azure · GCP. Terraform module ships at contract.
Model weights
Owned by the customer
Fine-tune runs inside the cluster. No external checkpoints.
Data egress
Zero, by architecture
No candidate PII, transcripts, or embeddings leave the boundary.
Audit
Signed decision trace
SIEM stream, hash-chained per req, reproducible on retrain.
See the thirteen agents run against your own data.
A 30-minute working session. NODES models the cohort or scope you bring, scores a hold-out, and shows the Decision Trace for three real decisions you have already made: hires, HR tickets, deals, or comp decisions. Bring whichever you want to test.