This is the "agents.vxs.ai" view — every agent that has a name and a job, in one place.
Sara
Ops Sentinel — Jira chase/nudge engine, escalation, fire alerts
LIVE since 14-Jul-2026
DigitalOcean droplet
Scans stuck Jira items on a schedule, nudges the owner directly by email (no human drafts or sends it), tracks follow-ups, and escalates to Apurva after 3 unanswered nudges or no resolvable owner. First live run: 207 real nudges, 0 errors.
Runs on: standalone droplet (139.59.24.166), not Cowork
Owner: Apurva Mankad
⚠️ Not in webxpress-servers inventory yet. Not visible/pauseable from Cowork — needs SSH to change.
Mira
Delivery Ops — daily brief, weekly PM scorecard, ETA chasers
Active daily
Reporting only
Fully automated report generation and send — daily project brief (~05:30 IST), weekly PM scorecard, event-driven Jira ETA chaser emails. Nobody reviews these before they go out.
Sends as: Mira@webxpress.in
Underlying: customer-project-tracker skill
⚠️ Skill not yet installed in Cowork Settings → Capabilities. No GitHub repo of her own. Scheduled task not registered/visible in Cowork.
Sharon
Marketing — campaign drafting, send, performance reporting
Human approval gate
Drafts the full campaign (brief → HTML email → Brevo send → stats digest) but every send is gated on Apurva's approval. By design, not a gap — but it means Sharon is an accelerant, not a replacement, for that step.
Sends via: Brevo
Skills: sharon, send-mail, apurva-voice, theme-factory
Baldev
Control Tower — chases drivers/transporters on HawkEye events
Not confirmed live
Proposed voice/call layer for HawkEye: vehicle delayed, checkpoint missed, driver unreachable → Baldev calls/messages the relevant party. This is the one agent that would replace a human phone call, not just a nudge.
Repo: hawkeye-codeagent (flagged "production structurally unreachable")
⚠️ Open questions: is he actually calling anyone today? Voice, WhatsApp, or both? No Twilio caller ID confirmed. This is the biggest "is it real or paper" gap in the ecosystem.
Honest classification of what each agent function does today. Level 3 = genuinely closes the loop with zero human touch, end to end. Most of the ecosystem sits at Level 1–2: it tells a human what to do, faster and more reliably than before — which is real value, but it is not headcount-replacing work yet.
| Function | Agent | Autonomy today | What's still human |
|---|
| Jira stuck-item nudge | Sara | L3 — fully closed | Nothing — nudge is sent and escalated with no review |
| Daily ops brief | Mira | L3 — fully closed | Apurva still has to read it and decide what to act on |
| PM productivity scorecard | Mira | L3 — fully closed | Same — generated and sent, but it's a report, not an action |
| Marketing campaign send | Sharon | L1 — drafts only | Apurva approves every send before it goes out |
| Driver/transporter chase | Baldev | L0 — unconfirmed | Everything — likely still a phone call from ops today |
| Bug/ticket resolution | — | L0 — human only | Engineers still write every fix; agents only report and chase |
| Customer support resolution | — | L0 — human only | Sara scores/routes tickets; a person still answers them |
| GST / TDS filing | (skills, not agents) | L1 — draft/reconcile only | Filing itself and sign-off stay human — correctly, given liability |
1. Confirm and productionize Baldev, or shelve it
This is the only agent designed to replace a human action a person is doing right now (a phone call to a driver), rather than speeding up a report. Right now it's unclear if it's live at all. Worth a one-week push to get a real answer: is hawkeye-codeagent deployed, does it place a call or send WhatsApp, and on what trigger volume. If it's real, it's the highest-leverage agent in the fleet. If it's not, stop counting it as "done."
Why this first: it's the one place the roadmap already points at full automation — it just needs verification, not a new idea.
2. Let Sara auto-close, not just auto-nudge, on defined ticket types
Sara already nudges and escalates without review (L3). The next step is narrow but real: for a specific class of stuck items — e.g. "spec acknowledged, no update in 5 days, low severity" — let her auto-transition status or auto-close with a logged reason, instead of only nudging forever. Start with one non-critical ticket type as a pilot.
Why: it's a small extension of infrastructure that already works live, not a new build.
3. Tier-1 customer support answering, not just triage
Sara currently scores and routes support email/Teams threads but a person still answers every one. The WebXpress Wiki connector (43k files, semantic search) already exists. A pilot agent that auto-answers the most common, lowest-risk question categories (status checks, "how do I," known-issue lookups) end-to-end — with a hard fallback to a human for anything outside a confidence threshold — would be the first agent doing real customer-facing work without a person in the loop.
Why: support is the highest-volume repetitive human task visible in the ecosystem right now, and the knowledge base to answer from already exists.
4. Auto-send low-risk marketing sends, keep approval for the rest
Sharon's approval gate makes sense for new campaigns but is overkill for repeat, low-risk sends (e.g. a recurring newsletter with a fixed template, or a re-send to a segment that's already approved once). Tiering the approval gate by risk — auto-send for known-safe patterns, human approval only for new content or new audiences — would remove a human step without changing where judgment is actually needed.
Why: cheapest possible win — no new capability, just a policy change on an agent that already exists.
5. Bring Mira and Baldev fully under Cowork so they're governable
Mira's skill isn't installed in Cowork and her schedule isn't visible there; Sara lives entirely outside Cowork on a droplet reachable only by SSH. Before pushing any agent further toward "no human needed," the team needs to actually be able to see, pause, and audit what it's doing — right now that's only true for the Claude/Cowork-run pieces.
Why: this isn't a new automation, it's the visibility layer this whole exercise (this dashboard) is trying to establish — without it, "how far have we progressed" stays a guess.