Verifiable career facts and engineering judgment

Xinwei Xiong

AI Product Systems Engineer

Agent Engineering / Evaluation / Native iOS

Verified facts 2026-10-08

I build agent products around user scenarios, with durable context, failure recovery and tool policy across web and native iOS.

Help people and agents recover context and continue work across tools and sessions.

Engineering Signals

DayPage TestFlight v0.4.74 / 9 scheduled regressions / 464 tests + 4 UI flows
StripSearch SQLite recovery / Source withdrawal / Four export formats
OpenIM #1 contributor / 358 contributions / 11-service Helm / API + E2E CI

Selected Systems

Problem, ownership, decisions, validation, artifacts and boundaries

Ownership / Solo Product Engineer

DayPage

Apr 2026 - present Dogfood · Jul TestFlight v0.4.74

Native iOS capture and AI compilation with a Markdown/YAML vault, draft recovery and concurrent-write protection.

Problem / Constraint

Personal notes were fragmented across capture surfaces, making context hard to continue, inspect or reuse with agents.

Key Decisions

  • Chose a Markdown and YAML file-system vault instead of an opaque database.
  • Used BGTaskScheduler for nightly AI compilation with backfill and local failure notifications.
  • Made the compilation endpoint configurable through an OpenAI-compatible base URL and model so storage and workflows are not bound to one provider.

Validation / Outcomes

  • Public automation delivered TestFlight v0.4.74, with the matching prerelease providing a signed distribution IPA under a fixed SHA-256; nine scheduled regressions succeeded from 22 to 30 Jul 2026, with the latest completing 187 XCTest, 277 Swift Testing tests with 4 known issues recorded by the test framework, and 4/4 Maestro UI flows.
  • Implemented up to seven-day backfill; Local-to-iCloud vault migration checks file counts and sampled SHA-256 hashes before switching, retains the local backup, and is covered by scheduled CI.
  • The owner's fact card records a local vault spanning about 250 days of Markdown; this is context-corpus scale, not consecutive usage or external-user count.
  • A pinned September commit adds per-record serialized writes, durable draft recovery and cleanup after persistence confirmation, preserving local conflicts before remote replacement.

Boundary / Not Yet Proven

TestFlight v0.4.74 and the scheduled-regression figures are July 2026 verification snapshots; September changes are pinned source-code evidence. The full Skills → Agent Execution → UI Artifacts flow remains a proposal; external adoption, real-device background reliability and the current distributed build were not verified in this review.

Ownership / Product design and AI-assisted engineering

StripSearch

Sep 2026 - present Workspace live · Research unavailable

Person research with traceable evidence, persistent progress and JSON / Markdown / HTML / PDF exports.

Problem / Constraint

Person research spans multiple sources; interrupted runs and withdrawn sources require preserved progress and revalidated conclusions.

Key Decisions

  • Persist checkpoints, action reservations and receipts in SQLite; reuse successful actions and stop uncertain paid calls while retaining collected material.
  • Drive four export formats from one structured report; invalidate dependent conclusions after source withdrawal and recheck the report around export.

Validation / Outcomes

  • Implemented research-controller recovery, cancellation and action records, and delivered an authenticated, account-isolated workspace with JSON, Markdown, HTML and PDF exports.
  • Public CI succeeded for the pinned 8 Oct 2026 commit; its PR records 787 passing web tests, one skip and 40 frozen offline replays. These checks cover execution contracts rather than person-research quality.

Boundary / Not Yet Proven

The 8 Oct 2026 deployment has no provider credentials, so live research returns provider_unavailable; the new Fetch pipeline still uses synthetic adapters. Workspace and export acceptance used synthetic reports and does not validate current live research, cross-platform collection, research quality or external adoption.

Ownership / Runtime Design and Implementation

Agentry

Jun 2026 · embedded prototype Working prototype

A resumable, auditable agent runtime that unifies loops, tools, sessions, policy and multiple transports.

Problem / Constraint

Agent applications often couple model calls, tool permissions, session recovery and protocol access, making them hard to test and audit.

Key Decisions

  • Defined Provider, Tool, Transport and Session as four stable seams.
  • Modeled sessions as logically appended event streams, persisted as JSONL snapshots and replayed to rebuild context.
  • Implemented allow, deny and ask policy primitives plus SSRF screening that rechecks DNS results, redirects and private address ranges.

Validation / Outcomes

  • Implemented a bounded agent loop, replayable JSONL sessions, cancellation-aware retries, HTTP and stdio runtime transports, stdio MCP client/server and agent-as-tool primitives.
  • The pinned public commit contains 191 top-level tests across 17 packages; build, vet, test and the race detector were reproduced at that commit with 63.2% statement coverage.

Boundary / Not Yet Proven

This remains a prototype inside the DayPage monorepo; repository CI does not run Agentry tests, the CDP browser package is untested, ask approval and sub-agent profiles are not wired into the CLI, and there is no independent release or external adoption evidence.

Go / MCP / JSON-RPC / HTTP / Chrome CDP / JSONL

Ownership / Workflow design and AI-assisted implementation

agent-kit

Sep 2026 - present Open-source personal tooling

A shared skill tree for six coding agents, with dry-run installation, idempotent symlinks and conflict preflight, plus third-party source/license validation and public-content scanning.

Boundary / Not Yet Proven

Installation and validation workflows are project work; third-party skills retain their authorship. Public CI verifies tool behavior without establishing external adoption, cost savings or model-quality gains. Rule-based scanning cannot guarantee removal of every secret.

Ownership / Solo Product Engineer

Solo Compass

May 2026 - present Pre-alpha · TestFlight v0.1.289

An AI-curated living map for solo travelers, validating prompts and schema with a bot before expanding to web and native iOS.

Validation / Outcomes

  • Public automation completed signing, Fastlane and TestFlight upload, version tagging, GitHub prerelease and IPA archival through v0.1.289.
  • Public CI validates TypeScript types, formatting, schema dry-runs, TypeScript-to-Swift data parity and gitleaks secret scanning.

Boundary / Not Yet Proven

The TestFlight upload is verifiable, but the separate iOS CI currently masks an xcodebuild destination error and cannot prove build or test success; the README also warns against production use, and external adoption remains unverified.

Ownership / Design and Implementation

CCT

May 2026 - present Public working prototype

A public working prototype that captures sessions through Claude Code Hooks and provides local search, browsing and statistics over SQLite and JSONL.

Python / FastAPI / SQLite/JSONL / React / Claude Code Hooks / WebSocket

Ownership / Solo Product Engineer

Telepace Next

Jul 2026 - present Revalidation prototype

A voice-native, agent-first user-research prototype exposed through MCP, web and REST/webhooks.

Boundary / Not Yet Proven

Public evidence currently shows repository activity in July 2026, not adoption or payment outcomes.

Python / Pydantic / MCP / PostgreSQL / TypeScript / Next.js

Ownership / Open-source Intern / Community Contributor

OpenIM

Public contribution window: Apr 2023 - Apr 2024 Past contribution

Owned deployment, CI and contributor governance in a large Go IM project; reached #1 on GitHub's contributor graph.

Problem / Constraint

As the project grew, deployment, testing, protocol explanations and community knowledge needed standardization for distributed collaboration.

Key Decisions

  • Treated deployment guides, protocol documentation and contribution workflows as engineering systems.
  • Coordinated across roles through issues, pull requests, biweekly meetings and asynchronous documentation.

Validation / Outcomes

  • Ranked first on the OpenIM Server default-branch contributor graph with 358 contributions; a public retrospective documents 100+ PRs and 100+ issues.
  • Representative merged work includes Helm Charts and Helmfile orchestration for 11 services (#1291), API and E2E testing in GitHub Actions (#1359), and the contributor baseline for RFCs, DCO, PR review and releases (#366).
  • Published eight long-form OpenIM videos from Oct 2023 to Jan 2024; a public-platform snapshot on 20 Jul 2026 records the top three at 4,736, 3,308 and 959 views.

Boundary / Not Yet Proven

The contribution count does not imply every commit was core IM server code; the resume separates engineering, documentation and community scope.

Ownership / Founder / Product Engineer

Telepace AI

Jun 2024 - Oct 2025 Paused

Led an AI feedback analysis SaaS spanning asynchronous data pipelines, real-time web interaction and Kubernetes deployment.

Problem / Constraint

Customer feedback arrived through fragmented forms and APIs and needed asynchronous aggregation, analysis and live presentation.

Key Decisions

  • Used a Django and Celery pipeline with a Next.js frontend and WebSocket delivery.
  • Built dual-region Kubernetes and multi-registry delivery too early, later identifying this as a sequencing error.

Validation / Outcomes

  • Led the core backend, system integration and deployment while collaborating on the web product; without reaching a first paying user, the initial venture stopped after 28 Oct 2025.
  • Turned the failure into explicit validation-first sequencing: a later public strategy sets gates of at least 100 signups or 20 paid preorders per concept within three weeks, and a pivot if a direction misses $2K MRR by month four. These are forward-looking kill criteria, not achieved results.

Boundary / Not Yet Proven

Paused refers only to the 2024 to 2025 initial venture. The 2026 prototype is listed separately; interview and trial counts still require owner confirmation.

Career timeline

From deployment and open-source collaboration at OpenIM to an AI SaaS venture and independent products; recent work connects user stories to evaluation cases and focuses on task recovery and result verification.

Remote

Telepace AI

Founder / Product Engineer

Founded an AI feedback analysis SaaS, owning the core backend, asynchronous data pipeline, system integration and Kubernetes delivery while collaborating on the web product. The stack worked end to end, but no first paying user emerged, so the initial venture stopped in 2025 and the lesson became explicit validation gates and kill criteria.

The Plant

Engineering Team Member

Briefly joined the international team of a Tokyo-based commerce software company during the final university year, then moved into independent entrepreneurship. Exact dates, formal title and a representative outcome remain pending.

Remote

OpenIM

Open-source Intern, then Community Contributor

The owner confirms sustained OpenIM community work from junior year through the final spring; a public retrospective records a six-month internship within that period, while exact employment dates remain pending. Currently ranked first on GitHub's contributor graph, with work across deployment, test automation, protocol and documentation clarification, and the Chinese community.

Work in Progress

agent-diff-guard

A local agent-governance tool that gates high-risk drift before push, deduplicates token usage by message ID, and ranks projects and sessions by estimated cost to expose runaway work.

Open-source dogfood Docs

voiceflow

Designed provider interfaces for a voice AI pipeline so STT, TTS, LLM and storage implementations could be swapped through shared abstractions and configuration.

Inactive Repository
Public Work Graph Products / Prototypes / Engineering Logs Statuses on product pages are editorial snapshots; delivery and adoption claims remain governed by this resume's evidence layer.

Writing & Open Source

I publish agent source-code research, product practice and monthly reflections. Recent writing connects user stories to success criteria, failure analysis and regression cases, and studies task and authorization boundaries in personal assistants.

Core Stack

Agent Systems
Agent loop / MCP / Tool policy / Session lifecycle / Computer Use / Provider abstraction
Product Systems
Native iOS / Web / Backend / TestFlight / Local-first
Validation
Task-specific eval design / Failure analysis / Regression testing / Artifact verification / CI/CD / XCTest / Swift Testing / Maestro / Go race detector
Languages
Swift / TypeScript / Go / Python
Education Wuhan College of Arts & Sciences / Computer Science · undergraduate studies completed / 2024

Claim Ledger

Public evidence and owner attestations are explicitly separated · Expand ↓Collapse ↑

claim.daypage.testflight

A public pipeline uploaded DayPage TestFlight v0.4.74 on 22 Jul 2026; the matching prerelease contains an 18,339,826-byte DayPage.ipa under a fixed SHA-256. A reproducible audit of the public IPA reads com.daypage.app, 0.4.74 (1879), minimum iOS 16.1, an App Store distribution profile and get-task-allow=false. This proves a distributable artifact, not external adoption or real-device reliability.

Public automation + reproducible artifact audit 2026-08-04 TestFlight delivery workflowDayPage v0.4.74 signed IPA prerelease
claim.daypage.ci

Nine consecutive public scheduled regressions succeeded from 22 to 30 Jul 2026; the latest completed 187 XCTest, 277 Swift Testing tests with 4 known issues recorded by the test framework, and 4/4 Maestro UI flows.

claim.daypage.vault

DayPage stores raw entries, daily pages and short-term memory in a Markdown and YAML file-system vault.

Public code 2026-08-04 DayPage repositoryDayPage AGENTS.md
claim.daypage.dogfood

DayPage is used for daily dogfooding; duration and external tester count remain pending.

Owner attestation 2026-08-04 DayPage daily dogfood statement
claim.daypage.vault_scale

The owner's fact card records a DayPage local vault spanning about 250 days of Markdown; this measures context-corpus span, not consecutive usage or external-user count.

Owner attestation 2026-08-04 DayPage vault corpus statement
claim.agentry.runtime

Agentry implements a bounded agent loop, replayable JSONL sessions, cancellation-aware HTTP retries, HTTP and stdio runtime transports, stdio MCP client/server, HTTP-tool SSRF defenses and agent-as-tool primitives.

Public code 2026-08-04 Agentry architectureAgentry source
claim.agentry.tests

The pinned public commit contains 191 top-level tests across 17 packages; go build, vet, test and the race detector were reproduced at that commit with 63.2% statement coverage, but repository CI does not yet run this suite.

Reproducible public code audit 2026-08-04 Agentry pinned runtime and test suite
claim.openim.rank

cubxxw currently ranks first on the OpenIM Server GitHub contributor graph with 358 contributions.

Public repository 2026-08-04 OpenIM Server contributors
claim.openim.internship

A public retrospective records a six-month internship within the OpenIM experience; exact employment dates remain pending.

Public self-authored retrospective 2026-08-04 OpenIM public retrospective
claim.openim.academic_stage

The owner confirms sustained OpenIM community participation from junior year through the final spring; the verifiable default-branch contribution window is Apr 2023 to Apr 2024.

Owner attestation + public repository 2026-08-04 OpenIM academic-stage statement by resume ownerOpenIM Server contributors
claim.openim.scope

OpenIM contributions covered engineering practices, deployment, CI and testing, contributor workflows, protocol and documentation work, and the Chinese community.

Public repository + owner retrospective 2026-08-04 OpenIM pull requests by cubxxwOpenIM public retrospective
claim.telepace.validation_gates

In a later public product strategy, the owner sets validation gates of at least 100 signups or 20 paid preorders per concept within three weeks, with a pivot if a direction misses $2K MRR by month four; these are future gates, not achieved results.

Public self-authored retrospective 2026-08-04 2026 product validation and kill-criteria strategy
claim.telepace.responsibility

An authenticated owner audit of the now-private Telepace repositories ranks the owner first in feedback-collection-api and server (577 / 279 contributions) and second in the multi-contributor web repository (162). This supports the responsibility boundary of leading the core backend and system integration while collaborating on the web product; because the repositories are not public, the figures remain owner-attested for public readers and do not demonstrate commercial adoption.

Private repository audit + owner attestation 2026-08-04 Telepace private repository responsibility audit (self-attested)
claim.telepace.nexus_alpha

The owner's fact card records real non-paying use of the Nexus alpha within the Telepace product line. Because no verifiable user count, activation cohort or retention cohort was retained, this resume treats it only as a qualitative contact signal rather than an adoption outcome.

Public repository + owner attestation 2026-08-04 Nexus public repositoryNexus alpha use statement (self-attested)
claim.telepace.next

Telepace Next is a publicly active July 2026 voice-native, agent-first user-research prototype.

Public repository 2026-08-04 Telepace Next repository
claim.solo.testflight

Solo Compass has a public TestFlight v0.1.289 upload plus passing TypeScript, schema-parity and secret-scan checks; its README still labels the product Pre-alpha, and a separate iOS workflow has a false positive that masks xcodebuild failure.

claim.voiceflow.lifecycle

The Git history currently visible in the public repository spans May 2023 to Apr 2025; GitHub does not mark the repository as archived.

Public repository 2026-08-04 voiceflow repository
claim.cct.prototype

CCT is a public working prototype using Claude Code Hooks, FastAPI, SQLite/JSONL and React.

Public code 2026-08-04 CCT repository
claim.theplant.employment

The owner reports working with The Plant K.K.'s engineering team for about two months in 2024; exact dates, formal title and outcomes remain pending.

Owner attestation 2026-08-04 The Plant employment statement by resume owner
claim.education.graduation

The owner reports completing undergraduate study at Wuhan College of Arts & Sciences in 2024 and states in a public annual review that Computer Science was the chosen major; the exact degree title remains pending.

Owner attestation + public retrospective 2026-08-04 Education statement by resume owner2024 public annual review
claim.theplant.transition

The owner's public annual review describes leaving a foreign-company role around graduation to pursue independent work and entrepreneurship; it does not name the employer, so it supports the career transition rather than formal The Plant employment.

Public self-authored retrospective 2026-08-04 2024 public annual review
claim.basics.public_profile

On 31 Jul 2026, the owner confirmed Shenzhen as the current location; the public GitHub profile still lists @Singapore with hireable=true, so that public location remains to be updated.

Owner attestation + public platform snapshot 2026-08-04 Current location statement by resume ownerCurrent public GitHub profile
claim.daypage.draft_recovery

The pinned 20 Sep 2026 commit implements durable draft recovery, cleanup after persistence confirmation, per-record serialized writes and local conflict preservation before remote replacement. This review checks code rather than certifying real-account sync or device reliability.

claim.stripsearch.recovery

Persist checkpoints, action reservations and receipts in SQLite; reuse successful actions and stop uncertain paid calls while retaining collected material.

claim.stripsearch.live_boundary

The 8 Oct 2026 deployment has no provider credentials, so live research returns provider_unavailable; the new Fetch pipeline still uses synthetic adapters. Workspace and export acceptance used synthetic reports and does not validate current live research, cross-platform collection, research quality or external adoption.

claim.agent_kit.installation

agent-kit provides dry-run and idempotent installation from a shared skill source for six coding agents. All-target preflight blocks writes on conflicts, resolved paths are rechecked before writes, and source commits, tree hashes and licenses are validated. Public CI checks tool behavior; third-party skills retain their authorship.

claim.writing.personal_agent_design

Public research uses pinned OpenClaw source to examine run recovery and tool policy, and proposes a reference model for mandates, tasks, runs and result verification. The article explicitly labels this a design example rather than an author-deployed, tested system.

Public self-authored retrospective 2026-10-08 Personal Agent technical study with explicit design boundaries
claim.writing.figwright

The public article records use of free Figwright; the personal design-system workflow and DayPage card exercise remain proposals rather than a delivered cross-platform design system.

Public self-authored retrospective 2026-10-08 Figwright usage and proposed design-system workflow

Evidence Register

Last verified 2026-10-08 · Expand ↓Collapse ↑

DayPage repository Public repository · 2026-07-31 DayPage AGENTS.md Source document · 2026-07-31 TestFlight delivery workflow Automation record · 2026-07-31 DayPage v0.4.74 signed IPA prerelease Release record · 2026-07-31 DayPage scheduled regression 9/9 (30 Jul) CI run · 2026-07-31 DayPage scheduled regression 8/9 (29 Jul) CI run · 2026-07-31 DayPage scheduled regression 7/9 (28 Jul) CI run · 2026-07-31 DayPage scheduled regression 6/9 (27 Jul) CI run · 2026-07-31 DayPage scheduled regression 5/9 (26 Jul) CI run · 2026-07-31 DayPage scheduled regression 4/9 (25 Jul) CI run · 2026-07-31 DayPage scheduled regression 3/9 (24 Jul) CI run · 2026-07-31 DayPage scheduled regression 2/9 (23 Jul) CI run · 2026-07-31 DayPage scheduled regression 1/9 (22 Jul) CI run · 2026-07-31 DayPage background compilation service Source code · 2026-07-31 DayPage background compilation tests Source code · 2026-07-31 DayPage vault migration service Source code · 2026-07-31 DayPage vault migration tests Source code · 2026-07-31
DayPage daily dogfood statement Owner attestation · 2026-07-31
DayPage vault corpus statement Owner attestation · 2026-07-31
Agentry architecture Source document · 2026-07-31 Agentry source Source code · 2026-07-31 Agentry pinned runtime and test suite Source code · 2026-07-31 OpenIM Server contributors Contributor graph · 2026-07-31 OpenIM pull requests by cubxxw Pull requests · 2026-07-31 OpenIM public retrospective Public retrospective · 2026-07-31
OpenIM academic-stage statement by resume owner Owner attestation · 2026-07-31
OpenIM long-form video reach on Bilibili Public platform snapshot · 2026-07-31 Representative OpenIM long-form deep-dive video Source document · 2026-07-31 OpenIM Helm Charts and Helmfile PR #1291 Pull requests · 2026-07-31 OpenIM API and E2E CI PR #1359 Pull requests · 2026-07-31 OpenIM contributor governance PR #366 Pull requests · 2026-07-31 Telepace GitHub organization Organization page · 2026-07-31 Telepace public repository activity Repository activity · 2026-07-31
Telepace private repository responsibility audit (self-attested) Owner attestation · 2026-07-31
Telepace owner statement (self-attested) Owner retrospective · 2026-07-31
Nexus public repository Public repository · 2026-07-31
Nexus alpha use statement (self-attested) Owner retrospective · 2026-07-31
Telepace Next repository Public repository · 2026-07-31 voiceflow repository Public repository · 2026-07-31 Solo Compass README Source document · 2026-07-31 Solo Compass TestFlight run Automation record · 2026-07-31 Solo Compass v0.1.289 prerelease Release record · 2026-07-31 Solo Compass TypeScript and schema validation run CI run · 2026-07-31 Solo Compass secret scan run CI run · 2026-07-31 Solo Compass iOS CI false-positive run CI run · 2026-07-31 CCT repository Public repository · 2026-07-31 The Plant company context (does not verify employment) Company information · 2026-07-31
The Plant employment statement by resume owner Owner attestation · 2026-07-31
Education statement by resume owner Owner attestation · 2026-07-31
2024 public annual review Public retrospective · 2026-07-31
Current location statement by resume owner Owner attestation · 2026-07-31
Current public GitHub profile Public platform snapshot · 2026-07-31 2026 product validation and kill-criteria strategy Public retrospective · 2026-07-31 agent-diff-guard README and local usage dashboard Source document · 2026-08-04 agent-diff-guard token aggregation and project ranking source Source code · 2026-08-04 DayPage September durable draft recovery Source code · 2026-10-08 DayPage September serialized record writes Source code · 2026-10-08 StripSearch recoverable research controller Source code · 2026-10-08 StripSearch four-format exports and snapshot rechecks Source code · 2026-10-08 StripSearch source withdrawal and dependent invalidation Source code · 2026-10-08 StripSearch successful CI at the 8 October release commit CI run · 2026-10-08 StripSearch October acceptance and live-provider limitations Pull requests · 2026-10-08 agent-kit installation preflight, source validation and public scan Source code · 2026-10-08 agent-kit successful tests and strict checks at pinned commit CI run · 2026-10-08 September 2026 public evaluation notes Public retrospective · 2026-10-08 October 2026 public user-story and evaluation notes Public retrospective · 2026-10-08 Personal Agent technical study with explicit design boundaries Public retrospective · 2026-10-08 Figwright usage and proposed design-system workflow Public retrospective · 2026-10-08