Vendor Case: How a Short-Drama Team Reworked Its R&D Workflow with Feishu AI

The case treats faster response as a workflow objective for short-drama operations.

In the short drama market, the golden window for a hit is extremely short. Whether a series can capture traffic and drive paid conversions largely depends on whether the front-end product has undergone repeated fine-tuning.

For Shanhai Xingchen, the mini-program is the central scene where change occurs.

The case article says Shanhai Xingchen was founded less than three years earlier and operates a large portfolio of short-drama IPs and mini-programs; the scale has not been independently verified here. Mini-programs connect distribution, conversion and monetization, so changes to activity configuration or payment experience may affect performance.

High-Frequency Iteration Challenges Collaboration Efficiency

High-frequency iteration tests collaboration among content, operations, product, R&D and testing teams. The case presents Feishu Projects AI and CodeM as tools in that chain; buyers should verify the applicable scope.

The Faster Business Accelerates, the Sooner Legacy Tools Hit Bottlenecks

A short-drama market window may be measured in weeks or days. From script review and production planning to mini-program development and testing, delays may increase delivery cost or miss a window; the impact should be measured with the team’s own data.

In its early days, Shanhai Xingchen relied on manual efforts to sustain growth. When there were only a few projects, creating chat groups, holding meetings, and circulating documents was manageable. However, as concurrent projects increased from a handful to dozens, the human-driven "chasing" model quickly approached its limits.

Testing lead Ouou said the downstream delivery team was sensitive to information gaps. The team reported that a PRD could take hours and that complex requirements involved repeated switching, organizing and re-entry across tools, which may increase data-transfer risk and handling time.

A more common bottleneck occurred after requirements entered the R&D phase: while product teams synced requirements, developers had to switch back locally to check code, pull branches, and confirm modification scopes—rebuilding context before development could begin. The more projects there were, the longer the waiting time.

The team realized that their existing toolset could no longer meet the needs of real-time decision-making.

Feishu CodeM, Embedded into the R&D Process

The case attributes changes in the R&D chain to integrating Feishu CodeM with the existing workflow; the effect has not been independently verified here.

As a native Feishu AI-powered R&D agent, CodeM functions as a coding agent tailored for enterprise R&D scenarios, seamlessly integrating into Feishu and Feishu Projects’ collaboration workflows to handle tasks such as feature development and bug fixing.

When a requirement flow reaches the "AI Development" stage, Feishu CodeM is designed to read the requirement and technical plan, perform requirement analysis, code modifications, and compilation verification within a cloud sandbox, then submit a merge request (MR), sync updates to Feishu Projects, and advance the task—capabilities buyers should confirm in a scoped demo.

The vendor describes a sandbox-based process with reduced manual steps and an engineer reviewing the MR. Buyers should confirm which actions require approval, what access the sandbox receives, and whether outputs can be reproduced in their own environment.

The case says frontend changes can move through the configured workflow; whether this reduces handoff delays should be measured in a pilot.

For short drama operations, this process not only saves coding time but, more importantly, reduces context-switching delays, tool transitions, and manual transmission lags during development. As AI continuously works along the workflow, the team’s core focus shifts from execution to judgment and decision-making.

Making AI an Integral Part of the Workflow

The transformation of the R&D agent from “waiting for instructions” to “scheduled within the workflow” stems from Shanhai Xingchen’s AI-driven workflow system built on Feishu Projects.

The case configures AI nodes across requirement drafting, technical review, testing, defect analysis and code development. Buyers should identify which tasks can trigger automatically and which still require human approval under the current edition, permissions and risk policy.

After a mini-program requirement is created, Feishu Projects automatically triggers an AI node that generates a structured PRD cloud document based on background, objectives, and constraints. Requirement approval and document generation are nearly completed simultaneously; the team reports that PRD drafting time fell substantially versus its earlier baseline, though buyers should measure the gain against their own drafting baseline in a pilot.

During technical reviews, AI proactively checks the completeness of plans, identifies missing elements, and suggests revisions. Review meetings no longer get bogged down in “what wasn’t clearly written,” but instead focus on critical design discussions, and enabling faster entry into development for new drama launches and campaign adjustments.

The vendor describes AI running specified test cases, drafting structured acceptance checklists, and proposing defect localization, causes, verification steps and remedies. Engineers should review every test result and remediation proposal; buyers can compare a controlled sample with their own defect-handling baseline.

Ouou described AI orchestration as “as simple as configuring a field.” The case says teams can place model capabilities in workflow nodes and reduce transfers between tools; this does not guarantee that data stays in one jurisdiction, so storage, transmission and access controls still require verification.

Smoother Workflows Lead to Easier Management

The impact of AI extends beyond coding and defect analysis. As it becomes embedded throughout the entire process, many management tasks previously requiring repeated confirmation, aggregation, and judgment now run automatically.

Every morning, managers receive an automated project insights report generated by the Feishu Projects assistant “Mili.” The AI summarizes progress across the team's ongoing projects and is designed to flag resource bottlenecks and review congestion, helping managers quickly pinpoint issues without manually checking each item.

Workforce analysis has shifted from “post-hoc statistics” to “preemptive planning.” Project managers can initiate AI-powered analysis via natural language queries to rapidly understand team workload, resource distribution, and potential conflicts—identifying risks before requirements kick off and enabling more reasonable scheduling.

The case says the team used AI to help reclassify historical change-reason records previously stored as “Other.” Classification accuracy and data quality require sample review; model output should not be treated as verified fact by default.

This continuous, online data accumulation has also transformed project retrospectives. The system automatically aggregates data on scheduling, working hours, defects, and documentation, generating retrospective reports that include execution summaries, progress analysis, and improvement recommendations.

At Shanhai Xingchen, AI is no longer just a tool for completing tasks—it has become an organic component that continuously participates in workflows, allows data to accumulate naturally within processes, and enables management actions to emerge seamlessly from workflows.

Accelerating Response Enables Faster Growth

The case links shorter workflow steps with faster response across content, operations, R&D and testing. Buyers should verify any improvement against delivery-cycle and review-quality baselines rather than assume a business advantage.

Zhou Peijin, Chairman and CEO of Shanhai Xingchen, said the company believed Feishu Projects supported its goals of improving efficiency, speed, quality and cost control. This is an attributed company statement, not an independently verified result.

These transformations have yielded results Shanhai Xingchen reports as measurable: the company says it has extended digitalization from content production to post-production, with faster document retrieval, shorter cross-departmental communication, and improved demand delivery. Buyers evaluating a similar platform should first measure their own baseline for document search time, meeting hours, and delivery cycle time in a pilot, so any efficiency gain can be judged against real numbers rather than vendor-shared figures.

In the short drama industry, time itself is competitiveness. When workflows operate smoothly, teams can dedicate more energy to the creative, content-related, and strategic decisions that determine a drama’s success. The value of Feishu Projects AI and Feishu CodeM lies precisely in pushing every requirement flow, collaboration, and delivery one step further.

If you are considering Feishu CodeM, request current edition, permission, data-handling and support details, then test a controlled, non-sensitive or approved sample workflow.